Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2530 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4191. Min Range: -8.4191
Max Act: 8.4191. Min Act: -0.1700
Data Index: 3450049 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4191. Min Range: -8.4191
Max Act: 8.3566. Min Act: -0.1700
Data Index: 6788675 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4191. Min Range: -8.4191
Max Act: 8.2941. Min Act: -0.1700
Data Index: 2136287 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4191. Min Range: -8.4191
Max Act: 8.2316. Min Act: -0.1700
Data Index: 7846448 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4191. Min Range: -8.4191
Max Act: 8.2316. Min Act: -0.1700
Data Index: 2597966 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4191. Min Range: -8.4191
Max Act: 8.1066. Min Act: -0.1700
Data Index: 131018 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4191. Min Range: -8.4191
Max Act: 8.1066. Min Act: -0.1700
Data Index: 4106672 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4191. Min Range: -8.4191
Max Act: 8.0441. Min Act: -0.1700
Data Index: 104622 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4191. Min Range: -8.4191
Max Act: 7.9816. Min Act: -0.1700
Data Index: 5801651 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4191. Min Range: -8.4191
Max Act: 8.0441. Min Act: -0.1700
Data Index: 33959 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4191. Min Range: -8.4191
Max Act: 7.9191. Min Act: -0.1700
Data Index: 8291706 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4191. Min Range: -8.4191
Max Act: 7.9191. Min Act: -0.1700
Data Index: 3441591 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4191. Min Range: -8.4191
Max Act: 7.9191. Min Act: -0.1700
Data Index: 2993448 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4191. Min Range: -8.4191
Max Act: 7.9191. Min Act: -0.1700
Data Index: 2254745 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4191. Min Range: -8.4191
Max Act: 7.9191. Min Act: -0.1700
Data Index: 6998129 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4191. Min Range: -8.4191
Max Act: 7.9191. Min Act: -0.1700
Data Index: 6100991 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4191. Min Range: -8.4191
Max Act: 7.9191. Min Act: -0.1700
Data Index: 5935042 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4191. Min Range: -8.4191
Max Act: 7.8566. Min Act: -0.1700
Data Index: 5585473 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4191. Min Range: -8.4191
Max Act: 7.8566. Min Act: -0.1700
Data Index: 4173722 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4191. Min Range: -8.4191
Max Act: 7.8566. Min Act: -0.1700
Data Index: 128352 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19