Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3099 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.8893. Min Act: -0.1700
Data Index: 5895859 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.8580. Min Act: -0.1700
Data Index: 4638855 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.6705. Min Act: -0.1700
Data Index: 7867359 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.6705. Min Act: -0.1700
Data Index: 22617 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.5768. Min Act: -0.1700
Data Index: 7899543 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.5455. Min Act: -0.1700
Data Index: 1087868 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.5455. Min Act: -0.1700
Data Index: 2501505 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.5455. Min Act: -0.1700
Data Index: 6909553 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.5143. Min Act: -0.1700
Data Index: 176631 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.4518. Min Act: -0.1700
Data Index: 6278700 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.4205. Min Act: -0.1700
Data Index: 1889902 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.4205. Min Act: -0.1700
Data Index: 5961783 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.3893. Min Act: -0.1700
Data Index: 2720511 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.3893. Min Act: -0.1700
Data Index: 8372071 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.3893. Min Act: -0.1700
Data Index: 4071001 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.3580. Min Act: -0.1700
Data Index: 8317927 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.3268. Min Act: -0.1700
Data Index: 706563 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.2955. Min Act: -0.1700
Data Index: 4760630 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.2955. Min Act: -0.1700
Data Index: 3480004 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8893. Min Range: -6.8893
Max Act: 6.2643. Min Act: -0.1700
Data Index: 2771401 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19