Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5686 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1191. Min Range: -3.1191
Max Act: 3.1191. Min Act: -0.1700
Data Index: 6778643 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1191. Min Range: -3.1191
Max Act: 3.0718. Min Act: -0.1700
Data Index: 6497342 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1191. Min Range: -3.1191
Max Act: 3.0718. Min Act: -0.1700
Data Index: 8193710 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1191. Min Range: -3.1191
Max Act: 3.0244. Min Act: -0.1700
Data Index: 7970306 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1191. Min Range: -3.1191
Max Act: 3.0244. Min Act: -0.1700
Data Index: 5262013 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1191. Min Range: -3.1191
Max Act: 3.0086. Min Act: -0.1700
Data Index: 1348438 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1191. Min Range: -3.1191
Max Act: 3.0086. Min Act: -0.1700
Data Index: 4364130 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1191. Min Range: -3.1191
Max Act: 2.9928. Min Act: -0.1700
Data Index: 2934159 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1191. Min Range: -3.1191
Max Act: 2.9770. Min Act: -0.1700
Data Index: 8549828 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1191. Min Range: -3.1191
Max Act: 2.9770. Min Act: -0.1700
Data Index: 6857349 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1191. Min Range: -3.1191
Max Act: 2.9770. Min Act: -0.1700
Data Index: 6316465 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1191. Min Range: -3.1191
Max Act: 2.9612. Min Act: -0.1700
Data Index: 7892106 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1191. Min Range: -3.1191
Max Act: 2.9612. Min Act: -0.1700
Data Index: 5668277 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1191. Min Range: -3.1191
Max Act: 2.9454. Min Act: -0.1700
Data Index: 3866362 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1191. Min Range: -3.1191
Max Act: 2.9454. Min Act: -0.1700
Data Index: 2987368 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1191. Min Range: -3.1191
Max Act: 2.9454. Min Act: -0.1700
Data Index: 4247048 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1191. Min Range: -3.1191
Max Act: 2.9454. Min Act: -0.1700
Data Index: 5656749 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1191. Min Range: -3.1191
Max Act: 2.9454. Min Act: -0.1700
Data Index: 6761533 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1191. Min Range: -3.1191
Max Act: 2.9454. Min Act: -0.1700
Data Index: 6229937 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1191. Min Range: -3.1191
Max Act: 2.9295. Min Act: -0.1700
Data Index: 7464497 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19