Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3300 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.4630. Min Act: -0.1700
Data Index: 7179937 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.2755. Min Act: -0.1700
Data Index: 2633975 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.2130. Min Act: -0.1700
Data Index: 2052669 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.1818. Min Act: -0.1700
Data Index: 4713326 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.1818. Min Act: -0.1700
Data Index: 5603431 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.1505. Min Act: -0.1700
Data Index: 1287639 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.1193. Min Act: -0.1700
Data Index: 143966 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.1505. Min Act: -0.1700
Data Index: 1566407 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.1193. Min Act: -0.1700
Data Index: 5981352 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.1193. Min Act: -0.1700
Data Index: 6658820 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.1193. Min Act: -0.1700
Data Index: 4192406 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.0568. Min Act: -0.1700
Data Index: 913528 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.0880. Min Act: -0.1700
Data Index: 266502 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.0880. Min Act: -0.1700
Data Index: 2667583 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.0880. Min Act: -0.1700
Data Index: 1354889 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.0880. Min Act: -0.1700
Data Index: 2238203 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.0568. Min Act: -0.1700
Data Index: 2104790 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.0880. Min Act: -0.1700
Data Index: 4558906 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.0568. Min Act: -0.1700
Data Index: 1566409 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4630. Min Range: -5.4630
Max Act: 5.0568. Min Act: -0.1700
Data Index: 10642 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19