Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2628 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.9535. Min Range: -11.9535
Max Act: 11.9535. Min Act: -0.1700
Data Index: 3643482 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9535. Min Range: -11.9535
Max Act: 11.5785. Min Act: -0.1700
Data Index: 5293314 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9535. Min Range: -11.9535
Max Act: 11.3285. Min Act: -0.1700
Data Index: 181363 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9535. Min Range: -11.9535
Max Act: 10.9535. Min Act: -0.1700
Data Index: 2918693 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9535. Min Range: -11.9535
Max Act: 10.8910. Min Act: -0.1700
Data Index: 4732787 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9535. Min Range: -11.9535
Max Act: 10.8910. Min Act: -0.1700
Data Index: 7791738 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9535. Min Range: -11.9535
Max Act: 10.8285. Min Act: -0.1700
Data Index: 4054916 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9535. Min Range: -11.9535
Max Act: 10.8285. Min Act: -0.1700
Data Index: 8146021 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9535. Min Range: -11.9535
Max Act: 10.7035. Min Act: -0.1700
Data Index: 6909828 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9535. Min Range: -11.9535
Max Act: 10.7035. Min Act: -0.1700
Data Index: 4671802 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9535. Min Range: -11.9535
Max Act: 10.5785. Min Act: -0.1700
Data Index: 8254804 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9535. Min Range: -11.9535
Max Act: 10.5160. Min Act: -0.1700
Data Index: 4907707 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9535. Min Range: -11.9535
Max Act: 10.5160. Min Act: -0.1700
Data Index: 7384353 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9535. Min Range: -11.9535
Max Act: 10.5160. Min Act: -0.1700
Data Index: 3570212 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9535. Min Range: -11.9535
Max Act: 10.3910. Min Act: -0.1700
Data Index: 6923152 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9535. Min Range: -11.9535
Max Act: 10.4535. Min Act: -0.1700
Data Index: 8389914 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9535. Min Range: -11.9535
Max Act: 10.3285. Min Act: -0.1700
Data Index: 3211374 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9535. Min Range: -11.9535
Max Act: 10.3285. Min Act: -0.1700
Data Index: 4632379 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9535. Min Range: -11.9535
Max Act: 10.3285. Min Act: -0.1700
Data Index: 4732786 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9535. Min Range: -11.9535
Max Act: 10.3285. Min Act: -0.1700
Data Index: 8010873 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19