Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3379 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3566. Min Range: -6.3566
Max Act: 6.3566. Min Act: -0.1700
Data Index: 4971075 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3566. Min Range: -6.3566
Max Act: 6.2628. Min Act: -0.1700
Data Index: 6694196 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3566. Min Range: -6.3566
Max Act: 6.0753. Min Act: -0.1700
Data Index: 3412771 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3566. Min Range: -6.3566
Max Act: 6.0128. Min Act: -0.1700
Data Index: 6361428 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.9816. Min Act: -0.1700
Data Index: 4011153 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3566. Min Range: -6.3566
Max Act: 6.0128. Min Act: -0.1700
Data Index: 1353119 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.9816. Min Act: -0.1700
Data Index: 7096252 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.9816. Min Act: -0.1700
Data Index: 3118393 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.9503. Min Act: -0.1700
Data Index: 7997829 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.9191. Min Act: -0.1700
Data Index: 3587630 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.9191. Min Act: -0.1700
Data Index: 2437429 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.8878. Min Act: -0.1700
Data Index: 1592041 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.8878. Min Act: -0.1700
Data Index: 1267649 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.8566. Min Act: -0.1700
Data Index: 3314612 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.8878. Min Act: -0.1700
Data Index: 1975537 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.8566. Min Act: -0.1700
Data Index: 8249381 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.8878. Min Act: -0.1700
Data Index: 2033215 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.7941. Min Act: -0.1700
Data Index: 1867387 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.8253. Min Act: -0.1700
Data Index: 8179622 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.8253. Min Act: -0.1700
Data Index: 3838862 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19