Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2863 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0367. Min Range: -7.0367
Max Act: 7.0367. Min Act: -0.1700
Data Index: 685760 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.8179. Min Act: -0.1700
Data Index: 4680364 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.6617. Min Act: -0.1700
Data Index: 5841808 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.6617. Min Act: -0.1700
Data Index: 5793957 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.6617. Min Act: -0.1700
Data Index: 1345135 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.6304. Min Act: -0.1700
Data Index: 3119178 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.5992. Min Act: -0.1700
Data Index: 3952190 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.6304. Min Act: -0.1700
Data Index: 5274054 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.5679. Min Act: -0.1700
Data Index: 3974907 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.5367. Min Act: -0.1700
Data Index: 2986645 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.5367. Min Act: -0.1700
Data Index: 772685 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.5054. Min Act: -0.1700
Data Index: 2046207 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.4742. Min Act: -0.1700
Data Index: 3552742 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.4117. Min Act: -0.1700
Data Index: 7943596 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.4117. Min Act: -0.1700
Data Index: 7694687 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.4117. Min Act: -0.1700
Data Index: 5590694 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.3804. Min Act: -0.1700
Data Index: 1406568 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.3804. Min Act: -0.1700
Data Index: 1419833 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.3804. Min Act: -0.1700
Data Index: 4115925 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0367. Min Range: -7.0367
Max Act: 6.3492. Min Act: -0.1700
Data Index: 6940208 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19