Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5509 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.9749. Min Act: -0.1700
Data Index: 8183496 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.7249. Min Act: -0.1700
Data Index: 6163721 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.5999. Min Act: -0.1700
Data Index: 417317 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.5374. Min Act: -0.1700
Data Index: 1373001 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.5999. Min Act: -0.1700
Data Index: 3042132 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.4749. Min Act: -0.1700
Data Index: 4418140 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.4749. Min Act: -0.1700
Data Index: 5183001 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.4749. Min Act: -0.1700
Data Index: 4062682 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.4749. Min Act: -0.1700
Data Index: 1387727 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.4749. Min Act: -0.1700
Data Index: 3178627 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.4124. Min Act: -0.1700
Data Index: 38396 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.3499. Min Act: -0.1700
Data Index: 2830671 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.3499. Min Act: -0.1700
Data Index: 19601 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.3499. Min Act: -0.1700
Data Index: 8472861 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.3499. Min Act: -0.1700
Data Index: 26611 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.3499. Min Act: -0.1700
Data Index: 1909134 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.3499. Min Act: -0.1700
Data Index: 7921608 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.3499. Min Act: -0.1700
Data Index: 7814685 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.3499. Min Act: -0.1700
Data Index: 6533015 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9749. Min Range: -8.9749
Max Act: 8.4124. Min Act: -0.1700
Data Index: 2905369 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19