Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.9806. Min Act: -0.1700
Data Index: 7870013 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.7931. Min Act: -0.1700
Data Index: 7527358 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.6368. Min Act: -0.1700
Data Index: 2336966 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.6368. Min Act: -0.1700
Data Index: 525579 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.6056. Min Act: -0.1700
Data Index: 4891746 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.6368. Min Act: -0.1700
Data Index: 3694457 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.5431. Min Act: -0.1700
Data Index: 7828661 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.5118. Min Act: -0.1700
Data Index: 7423013 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.5743. Min Act: -0.1700
Data Index: 8167628 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.5743. Min Act: -0.1700
Data Index: 1825553 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.4806. Min Act: -0.1700
Data Index: 1969506 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.4493. Min Act: -0.1700
Data Index: 4026357 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.4493. Min Act: -0.1700
Data Index: 5332 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.4493. Min Act: -0.1700
Data Index: 5938560 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.4181. Min Act: -0.1700
Data Index: 3880931 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.3868. Min Act: -0.1700
Data Index: 67799 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.3868. Min Act: -0.1700
Data Index: 4955000 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.3868. Min Act: -0.1700
Data Index: 4202805 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.3556. Min Act: -0.1700
Data Index: 5781911 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9806. Min Range: -5.9806
Max Act: 5.3243. Min Act: -0.1700
Data Index: 2583509 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19