Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 580 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.4020. Min Act: -0.1700
Data Index: 4552335 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.2145. Min Act: -0.1700
Data Index: 1954723 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.1207. Min Act: -0.1700
Data Index: 2622696 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.1207. Min Act: -0.1700
Data Index: 6721931 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0895. Min Act: -0.1700
Data Index: 150290 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0582. Min Act: -0.1700
Data Index: 5469359 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0270. Min Act: -0.1700
Data Index: 4826001 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0270. Min Act: -0.1700
Data Index: 7420274 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9957. Min Act: -0.1700
Data Index: 8114254 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9645. Min Act: -0.1700
Data Index: 1869576 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9957. Min Act: -0.1700
Data Index: 6719121 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9332. Min Act: -0.1700
Data Index: 2417769 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9332. Min Act: -0.1700
Data Index: 3707121 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9020. Min Act: -0.1700
Data Index: 5872590 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9332. Min Act: -0.1700
Data Index: 7823539 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9645. Min Act: -0.1700
Data Index: 3918761 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9332. Min Act: -0.1700
Data Index: 2791475 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9020. Min Act: -0.1700
Data Index: 3602789 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9332. Min Act: -0.1700
Data Index: 490632 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9332. Min Act: -0.1700
Data Index: 6686400 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19