Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3039 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.9518. Min Act: -0.1700
Data Index: 8340451 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.9205. Min Act: -0.1700
Data Index: 7390173 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.6393. Min Act: -0.1700
Data Index: 8677888 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.6705. Min Act: -0.1700
Data Index: 3708116 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.6393. Min Act: -0.1700
Data Index: 7095911 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.5768. Min Act: -0.1700
Data Index: 4035945 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.5143. Min Act: -0.1700
Data Index: 4420988 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.5143. Min Act: -0.1700
Data Index: 8805705 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.4830. Min Act: -0.1700
Data Index: 4915893 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.4518. Min Act: -0.1700
Data Index: 7118814 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.4205. Min Act: -0.1700
Data Index: 3273681 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.4205. Min Act: -0.1700
Data Index: 5599008 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.4205. Min Act: -0.1700
Data Index: 981701 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.3893. Min Act: -0.1700
Data Index: 8541728 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.3893. Min Act: -0.1700
Data Index: 4932069 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.3268. Min Act: -0.1700
Data Index: 8541729 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.3580. Min Act: -0.1700
Data Index: 4646479 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.3268. Min Act: -0.1700
Data Index: 3024036 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.3268. Min Act: -0.1700
Data Index: 3666243 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9518. Min Range: -6.9518
Max Act: 6.2643. Min Act: -0.1700
Data Index: 305532 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19