Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6295 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.7238. Min Act: -0.1700
Data Index: 3374946 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.5676. Min Act: -0.1700
Data Index: 8028490 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.5676. Min Act: -0.1700
Data Index: 4842102 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.5363. Min Act: -0.1700
Data Index: 7869523 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.5363. Min Act: -0.1700
Data Index: 2180301 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.4738. Min Act: -0.1700
Data Index: 8244086 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.4738. Min Act: -0.1700
Data Index: 286006 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.4738. Min Act: -0.1700
Data Index: 969888 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.4738. Min Act: -0.1700
Data Index: 6147631 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.4426. Min Act: -0.1700
Data Index: 6648108 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.4426. Min Act: -0.1700
Data Index: 413852 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.4426. Min Act: -0.1700
Data Index: 7808501 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.4426. Min Act: -0.1700
Data Index: 133212 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.4426. Min Act: -0.1700
Data Index: 8045544 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.3801. Min Act: -0.1700
Data Index: 1238331 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.3488. Min Act: -0.1700
Data Index: 4793791 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.3488. Min Act: -0.1700
Data Index: 34293 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.3488. Min Act: -0.1700
Data Index: 2824122 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.3176. Min Act: -0.1700
Data Index: 4376152 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7238. Min Range: -6.7238
Max Act: 6.3176. Min Act: -0.1700
Data Index: 6091318 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19