Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1776 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.8190. Min Act: -0.1700
Data Index: 4255804 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.8190. Min Act: -0.1700
Data Index: 6097783 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.6002. Min Act: -0.1700
Data Index: 127261 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.5377. Min Act: -0.1700
Data Index: 4374318 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.5377. Min Act: -0.1700
Data Index: 5444407 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.5065. Min Act: -0.1700
Data Index: 3397146 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.4440. Min Act: -0.1700
Data Index: 198726 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.3815. Min Act: -0.1700
Data Index: 6400395 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.3190. Min Act: -0.1700
Data Index: 2906712 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.3190. Min Act: -0.1700
Data Index: 6312313 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.2565. Min Act: -0.1700
Data Index: 1050079 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.2877. Min Act: -0.1700
Data Index: 7695240 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.2565. Min Act: -0.1700
Data Index: 1111549 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.2252. Min Act: -0.1700
Data Index: 2249624 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.2252. Min Act: -0.1700
Data Index: 5387439 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.1940. Min Act: -0.1700
Data Index: 6443220 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.2252. Min Act: -0.1700
Data Index: 3296676 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.2252. Min Act: -0.1700
Data Index: 83916 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.1627. Min Act: -0.1700
Data Index: 1840543 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8190. Min Range: -6.8190
Max Act: 6.1940. Min Act: -0.1700
Data Index: 5048973 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19