Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4979 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1684. Min Range: -7.1684
Max Act: 7.1684. Min Act: -0.1700
Data Index: 3497258 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.9809. Min Act: -0.1700
Data Index: 5311655 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.8559. Min Act: -0.1700
Data Index: 4864274 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.8246. Min Act: -0.1700
Data Index: 6014247 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.7621. Min Act: -0.1700
Data Index: 4936212 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.7309. Min Act: -0.1700
Data Index: 7960412 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.6996. Min Act: -0.1700
Data Index: 1047606 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.6996. Min Act: -0.1700
Data Index: 7776486 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.6684. Min Act: -0.1700
Data Index: 7426738 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.6371. Min Act: -0.1700
Data Index: 7572810 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.6059. Min Act: -0.1700
Data Index: 2974095 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.6371. Min Act: -0.1700
Data Index: 4380455 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.6371. Min Act: -0.1700
Data Index: 790061 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.6059. Min Act: -0.1700
Data Index: 2276872 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.6059. Min Act: -0.1700
Data Index: 8820494 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.5434. Min Act: -0.1700
Data Index: 217574 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.5746. Min Act: -0.1700
Data Index: 4144971 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.5434. Min Act: -0.1700
Data Index: 4589466 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.5746. Min Act: -0.1700
Data Index: 6907508 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1684. Min Range: -7.1684
Max Act: 6.5434. Min Act: -0.1700
Data Index: 589377 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19