Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3335 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4271. Min Range: -8.4271
Max Act: 8.4271. Min Act: -0.1700
Data Index: 3333795 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4271. Min Range: -8.4271
Max Act: 8.3646. Min Act: -0.1700
Data Index: 7483716 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4271. Min Range: -8.4271
Max Act: 8.1146. Min Act: -0.1700
Data Index: 2893239 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4271. Min Range: -8.4271
Max Act: 8.0521. Min Act: -0.1700
Data Index: 8138307 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4271. Min Range: -8.4271
Max Act: 8.0521. Min Act: -0.1700
Data Index: 4249042 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4271. Min Range: -8.4271
Max Act: 7.9584. Min Act: -0.1700
Data Index: 1849704 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4271. Min Range: -8.4271
Max Act: 7.9271. Min Act: -0.1700
Data Index: 7977106 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4271. Min Range: -8.4271
Max Act: 7.8959. Min Act: -0.1700
Data Index: 3056073 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4271. Min Range: -8.4271
Max Act: 7.7396. Min Act: -0.1700
Data Index: 4642272 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4271. Min Range: -8.4271
Max Act: 7.7396. Min Act: -0.1700
Data Index: 937194 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4271. Min Range: -8.4271
Max Act: 7.7396. Min Act: -0.1700
Data Index: 718934 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4271. Min Range: -8.4271
Max Act: 7.6459. Min Act: -0.1700
Data Index: 3894665 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4271. Min Range: -8.4271
Max Act: 7.5834. Min Act: -0.1700
Data Index: 1434732 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4271. Min Range: -8.4271
Max Act: 7.5834. Min Act: -0.1700
Data Index: 4710817 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4271. Min Range: -8.4271
Max Act: 7.5834. Min Act: -0.1700
Data Index: 3056074 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4271. Min Range: -8.4271
Max Act: 7.5521. Min Act: -0.1700
Data Index: 4084206 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4271. Min Range: -8.4271
Max Act: 7.5209. Min Act: -0.1700
Data Index: 4353261 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4271. Min Range: -8.4271
Max Act: 7.4896. Min Act: -0.1700
Data Index: 1312404 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4271. Min Range: -8.4271
Max Act: 7.4896. Min Act: -0.1700
Data Index: 6937828 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4271. Min Range: -8.4271
Max Act: 7.5209. Min Act: -0.1700
Data Index: 1792300 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19