Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2491 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6171. Min Range: -6.6171
Max Act: 6.6171. Min Act: -0.1700
Data Index: 7013184 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6171. Min Range: -6.6171
Max Act: 6.1796. Min Act: -0.1700
Data Index: 5133936 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6171. Min Range: -6.6171
Max Act: 5.8671. Min Act: -0.1700
Data Index: 6320751 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6171. Min Range: -6.6171
Max Act: 5.9296. Min Act: -0.1700
Data Index: 8424777 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6171. Min Range: -6.6171
Max Act: 5.9296. Min Act: -0.1700
Data Index: 5704727 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6171. Min Range: -6.6171
Max Act: 5.8358. Min Act: -0.1700
Data Index: 7105056 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6171. Min Range: -6.6171
Max Act: 5.7733. Min Act: -0.1700
Data Index: 2760381 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6171. Min Range: -6.6171
Max Act: 5.8358. Min Act: -0.1700
Data Index: 1475983 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6171. Min Range: -6.6171
Max Act: 5.7108. Min Act: -0.1700
Data Index: 5224682 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6171. Min Range: -6.6171
Max Act: 5.6796. Min Act: -0.1700
Data Index: 2969531 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6171. Min Range: -6.6171
Max Act: 5.6796. Min Act: -0.1700
Data Index: 1211278 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6171. Min Range: -6.6171
Max Act: 5.6483. Min Act: -0.1700
Data Index: 5679145 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6171. Min Range: -6.6171
Max Act: 5.5858. Min Act: -0.1700
Data Index: 8062149 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6171. Min Range: -6.6171
Max Act: 5.6171. Min Act: -0.1700
Data Index: 628538 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6171. Min Range: -6.6171
Max Act: 5.5546. Min Act: -0.1700
Data Index: 3241041 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6171. Min Range: -6.6171
Max Act: 5.5546. Min Act: -0.1700
Data Index: 2546080 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6171. Min Range: -6.6171
Max Act: 5.5546. Min Act: -0.1700
Data Index: 1407921 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6171. Min Range: -6.6171
Max Act: 5.5546. Min Act: -0.1700
Data Index: 8053104 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6171. Min Range: -6.6171
Max Act: 5.4921. Min Act: -0.1700
Data Index: 6483315 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6171. Min Range: -6.6171
Max Act: 5.5858. Min Act: -0.1700
Data Index: 5406704 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19