Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3840. Min Range: -8.3840
Max Act: 8.3840. Min Act: -0.1700
Data Index: 1606660 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3840. Min Range: -8.3840
Max Act: 8.3215. Min Act: -0.1700
Data Index: 301736 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3840. Min Range: -8.3840
Max Act: 8.1340. Min Act: -0.1700
Data Index: 1606656 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3840. Min Range: -8.3840
Max Act: 8.0715. Min Act: -0.1700
Data Index: 5845727 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3840. Min Range: -8.3840
Max Act: 8.0402. Min Act: -0.1700
Data Index: 4681924 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3840. Min Range: -8.3840
Max Act: 7.9777. Min Act: -0.1700
Data Index: 4607412 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3840. Min Range: -8.3840
Max Act: 8.0090. Min Act: -0.1700
Data Index: 758609 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3840. Min Range: -8.3840
Max Act: 7.9777. Min Act: -0.1699
Data Index: 4282031 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3840. Min Range: -8.3840
Max Act: 7.9465. Min Act: -0.1700
Data Index: 607459 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3840. Min Range: -8.3840
Max Act: 7.9465. Min Act: -0.1700
Data Index: 4626818 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3840. Min Range: -8.3840
Max Act: 7.9152. Min Act: -0.1700
Data Index: 2934793 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3840. Min Range: -8.3840
Max Act: 7.9465. Min Act: -0.1700
Data Index: 594791 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3840. Min Range: -8.3840
Max Act: 7.8840. Min Act: -0.1700
Data Index: 5241796 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3840. Min Range: -8.3840
Max Act: 7.8840. Min Act: -0.1700
Data Index: 340874 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3840. Min Range: -8.3840
Max Act: 7.9152. Min Act: -0.1700
Data Index: 7483514 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3840. Min Range: -8.3840
Max Act: 7.8840. Min Act: -0.1700
Data Index: 7047479 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3840. Min Range: -8.3840
Max Act: 7.8840. Min Act: -0.1699
Data Index: 646857 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3840. Min Range: -8.3840
Max Act: 7.8527. Min Act: -0.1700
Data Index: 2484390 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3840. Min Range: -8.3840
Max Act: 7.8527. Min Act: -0.1700
Data Index: 6434207 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3840. Min Range: -8.3840
Max Act: 7.8527. Min Act: -0.1700
Data Index: 6613100 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19