Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4083 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.5313. Min Act: -0.1700
Data Index: 178274 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.4375. Min Act: -0.1700
Data Index: 7366838 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.4375. Min Act: -0.1700
Data Index: 515058 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.3750. Min Act: -0.1700
Data Index: 7135205 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.3438. Min Act: -0.1700
Data Index: 95688 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.2813. Min Act: -0.1700
Data Index: 3631281 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.2813. Min Act: -0.1700
Data Index: 496377 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.2188. Min Act: -0.1700
Data Index: 5974344 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.2188. Min Act: -0.1700
Data Index: 1818599 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.2188. Min Act: -0.1700
Data Index: 4504465 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.2188. Min Act: -0.1700
Data Index: 7179511 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.2188. Min Act: -0.1700
Data Index: 314810 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.1563. Min Act: -0.1700
Data Index: 3903622 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.1563. Min Act: -0.1700
Data Index: 4171070 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.1250. Min Act: -0.1700
Data Index: 7263829 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.1250. Min Act: -0.1700
Data Index: 869040 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.1250. Min Act: -0.1700
Data Index: 803320 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.1250. Min Act: -0.1700
Data Index: 3697204 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.0938. Min Act: -0.1700
Data Index: 2679581 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5313. Min Range: -6.5313
Max Act: 6.0938. Min Act: -0.1700
Data Index: 4680101 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19