Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2258 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.9871. Min Act: -0.1700
Data Index: 7552839 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.7996. Min Act: -0.1700
Data Index: 3250141 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.7996. Min Act: -0.1700
Data Index: 7759063 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.7371. Min Act: -0.1700
Data Index: 2667434 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.7371. Min Act: -0.1700
Data Index: 2832462 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.7371. Min Act: -0.1700
Data Index: 5086941 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.7371. Min Act: -0.1700
Data Index: 4256867 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.7371. Min Act: -0.1700
Data Index: 1708199 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.7058. Min Act: -0.1700
Data Index: 6787443 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.6746. Min Act: -0.1700
Data Index: 3066213 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.6746. Min Act: -0.1700
Data Index: 5996317 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.6121. Min Act: -0.1700
Data Index: 2576124 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.5496. Min Act: -0.1700
Data Index: 358238 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.5496. Min Act: -0.1700
Data Index: 5167715 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.5496. Min Act: -0.1700
Data Index: 4043728 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.5183. Min Act: -0.1700
Data Index: 7216075 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.4871. Min Act: -0.1700
Data Index: 4314436 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.4871. Min Act: -0.1700
Data Index: 7190390 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.4871. Min Act: -0.1700
Data Index: 959056 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9871. Min Range: -6.9871
Max Act: 6.4558. Min Act: -0.1700
Data Index: 7208680 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19