Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2267 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.9004. Min Act: -0.1700
Data Index: 5150338 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.7128. Min Act: -0.1700
Data Index: 2614435 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.7284. Min Act: -0.1700
Data Index: 7205806 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.7284. Min Act: -0.1700
Data Index: 771414 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.7284. Min Act: -0.1700
Data Index: 5868525 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.7128. Min Act: -0.1700
Data Index: 7311904 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.6815. Min Act: -0.1700
Data Index: 1107591 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.6658. Min Act: -0.1700
Data Index: 3374248 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.6658. Min Act: -0.1700
Data Index: 1996294 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.6502. Min Act: -0.1700
Data Index: 8540435 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.6502. Min Act: -0.1700
Data Index: 7476324 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.6345. Min Act: -0.1700
Data Index: 3198193 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.6345. Min Act: -0.1700
Data Index: 3925168 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.6189. Min Act: -0.1700
Data Index: 5413722 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.6189. Min Act: -0.1700
Data Index: 5743119 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.6189. Min Act: -0.1700
Data Index: 6184715 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.6189. Min Act: -0.1700
Data Index: 8514445 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.6189. Min Act: -0.1700
Data Index: 3113039 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.5876. Min Act: -0.1700
Data Index: 2819662 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9004. Min Range: -3.9004
Max Act: 3.6189. Min Act: -0.1700
Data Index: 2107835 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19