Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1692 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.8901. Min Act: -0.1700
Data Index: 4158772 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.8589. Min Act: -0.1700
Data Index: 5631094 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.8589. Min Act: -0.1700
Data Index: 7580368 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.8276. Min Act: -0.1700
Data Index: 5619792 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.7026. Min Act: -0.1700
Data Index: 8255400 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6714. Min Act: -0.1700
Data Index: 8553811 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6401. Min Act: -0.1700
Data Index: 220151 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6089. Min Act: -0.1700
Data Index: 8126206 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6714. Min Act: -0.1700
Data Index: 7531533 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6401. Min Act: -0.1700
Data Index: 7031008 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6401. Min Act: -0.1700
Data Index: 7952547 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6089. Min Act: -0.1700
Data Index: 4438829 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6089. Min Act: -0.1700
Data Index: 2168001 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5464. Min Act: -0.1700
Data Index: 5149487 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5464. Min Act: -0.1700
Data Index: 1565413 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5464. Min Act: -0.1700
Data Index: 4165425 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5464. Min Act: -0.1700
Data Index: 7441385 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5464. Min Act: -0.1700
Data Index: 2920721 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5464. Min Act: -0.1700
Data Index: 4714027 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5151. Min Act: -0.1700
Data Index: 7038859 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19