Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 355 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4102. Min Range: -10.4102
Max Act: 10.4102. Min Act: -0.1700
Data Index: 7512859 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4102. Min Range: -10.4102
Max Act: 10.4102. Min Act: -0.1700
Data Index: 2169718 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4102. Min Range: -10.4102
Max Act: 10.2227. Min Act: -0.1700
Data Index: 6077663 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4102. Min Range: -10.4102
Max Act: 10.1602. Min Act: -0.1700
Data Index: 3483473 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4102. Min Range: -10.4102
Max Act: 10.1602. Min Act: -0.1700
Data Index: 6299255 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4102. Min Range: -10.4102
Max Act: 10.0352. Min Act: -0.1700
Data Index: 7133968 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4102. Min Range: -10.4102
Max Act: 9.9727. Min Act: -0.1700
Data Index: 4993045 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4102. Min Range: -10.4102
Max Act: 9.9102. Min Act: -0.1700
Data Index: 39267 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4102. Min Range: -10.4102
Max Act: 9.8477. Min Act: -0.1700
Data Index: 8788503 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4102. Min Range: -10.4102
Max Act: 9.8477. Min Act: -0.1700
Data Index: 160979 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4102. Min Range: -10.4102
Max Act: 9.8477. Min Act: -0.1700
Data Index: 8508194 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4102. Min Range: -10.4102
Max Act: 9.8477. Min Act: -0.1700
Data Index: 8190867 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4102. Min Range: -10.4102
Max Act: 9.8477. Min Act: -0.1700
Data Index: 4380296 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4102. Min Range: -10.4102
Max Act: 9.8477. Min Act: -0.1700
Data Index: 455429 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4102. Min Range: -10.4102
Max Act: 9.7852. Min Act: -0.1700
Data Index: 4168372 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4102. Min Range: -10.4102
Max Act: 9.7852. Min Act: -0.1700
Data Index: 3871691 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4102. Min Range: -10.4102
Max Act: 9.7227. Min Act: -0.1700
Data Index: 1232473 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4102. Min Range: -10.4102
Max Act: 9.7227. Min Act: -0.1700
Data Index: 7329442 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4102. Min Range: -10.4102
Max Act: 9.7227. Min Act: -0.1700
Data Index: 320927 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4102. Min Range: -10.4102
Max Act: 9.7227. Min Act: -0.1700
Data Index: 39265 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19