Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4292 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.8130. Min Act: -0.1700
Data Index: 8819621 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.8130. Min Act: -0.1700
Data Index: 4015854 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.7817. Min Act: -0.1700
Data Index: 3263886 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.8130. Min Act: -0.1700
Data Index: 1089684 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.7817. Min Act: -0.1700
Data Index: 8303524 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.7661. Min Act: -0.1700
Data Index: 8581715 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.7348. Min Act: -0.1700
Data Index: 2966232 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.7035. Min Act: -0.1700
Data Index: 5430381 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.7035. Min Act: -0.1700
Data Index: 8488105 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.7192. Min Act: -0.1700
Data Index: 5659361 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.7035. Min Act: -0.1700
Data Index: 5363236 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.7035. Min Act: -0.1700
Data Index: 1456518 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.7035. Min Act: -0.1700
Data Index: 7544522 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.6879. Min Act: -0.1700
Data Index: 5471681 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.6566. Min Act: -0.1700
Data Index: 6839434 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.6409. Min Act: -0.1700
Data Index: 8372184 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.6409. Min Act: -0.1700
Data Index: 816649 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.6096. Min Act: -0.1700
Data Index: 8065942 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.6253. Min Act: -0.1700
Data Index: 8480804 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8130. Min Range: -3.8130
Max Act: 3.6253. Min Act: -0.1700
Data Index: 6852768 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19