Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2896 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.9636. Min Act: -0.1700
Data Index: 2829882 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.6823. Min Act: -0.1700
Data Index: 897182 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.6823. Min Act: -0.1700
Data Index: 8257234 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.6511. Min Act: -0.1700
Data Index: 839641 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.5573. Min Act: -0.1700
Data Index: 7759808 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.5261. Min Act: -0.1700
Data Index: 7114554 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.4948. Min Act: -0.1700
Data Index: 3851853 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.4948. Min Act: -0.1700
Data Index: 8209037 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.5261. Min Act: -0.1700
Data Index: 748756 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.4323. Min Act: -0.1700
Data Index: 7505839 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.4636. Min Act: -0.1700
Data Index: 3590237 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.4011. Min Act: -0.1700
Data Index: 3517742 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.4011. Min Act: -0.1700
Data Index: 2525552 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.3698. Min Act: -0.1700
Data Index: 8014723 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.3698. Min Act: -0.1700
Data Index: 317525 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.3698. Min Act: -0.1700
Data Index: 7461034 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.3698. Min Act: -0.1700
Data Index: 5717411 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.3386. Min Act: -0.1700
Data Index: 7569020 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.3386. Min Act: -0.1700
Data Index: 4778885 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9636. Min Range: -6.9636
Max Act: 6.3386. Min Act: -0.1700
Data Index: 6693094 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19