Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2895 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4541. Min Range: -6.4541
Max Act: 6.4541. Min Act: -0.1700
Data Index: 8068455 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4541. Min Range: -6.4541
Max Act: 6.3291. Min Act: -0.1700
Data Index: 3022204 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4541. Min Range: -6.4541
Max Act: 6.2353. Min Act: -0.1700
Data Index: 6645646 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4541. Min Range: -6.4541
Max Act: 6.2041. Min Act: -0.1700
Data Index: 5768979 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4541. Min Range: -6.4541
Max Act: 6.1103. Min Act: -0.1700
Data Index: 4539407 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4541. Min Range: -6.4541
Max Act: 6.1103. Min Act: -0.1700
Data Index: 1168924 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4541. Min Range: -6.4541
Max Act: 6.0478. Min Act: -0.1700
Data Index: 1224485 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4541. Min Range: -6.4541
Max Act: 5.9853. Min Act: -0.1700
Data Index: 1002171 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4541. Min Range: -6.4541
Max Act: 5.9541. Min Act: -0.1700
Data Index: 2235463 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4541. Min Range: -6.4541
Max Act: 5.9228. Min Act: -0.1700
Data Index: 6339162 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4541. Min Range: -6.4541
Max Act: 5.9228. Min Act: -0.1700
Data Index: 1715844 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4541. Min Range: -6.4541
Max Act: 5.9228. Min Act: -0.1700
Data Index: 3749146 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4541. Min Range: -6.4541
Max Act: 5.8916. Min Act: -0.1700
Data Index: 7902460 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4541. Min Range: -6.4541
Max Act: 5.9228. Min Act: -0.1700
Data Index: 5930322 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4541. Min Range: -6.4541
Max Act: 5.8603. Min Act: -0.1700
Data Index: 7298697 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4541. Min Range: -6.4541
Max Act: 5.8291. Min Act: -0.1700
Data Index: 7225017 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4541. Min Range: -6.4541
Max Act: 5.7978. Min Act: -0.1700
Data Index: 95484 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4541. Min Range: -6.4541
Max Act: 5.7666. Min Act: -0.1700
Data Index: 4645537 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4541. Min Range: -6.4541
Max Act: 5.7666. Min Act: -0.1700
Data Index: 1242082 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4541. Min Range: -6.4541
Max Act: 5.7353. Min Act: -0.1700
Data Index: 808434 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19