Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.5726. Min Act: -0.1700
Data Index: 2488759 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.5101. Min Act: -0.1700
Data Index: 8322130 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.5101. Min Act: -0.1700
Data Index: 2030850 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.4476. Min Act: -0.1700
Data Index: 7070904 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.4163. Min Act: -0.1700
Data Index: 8411860 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.3851. Min Act: -0.1700
Data Index: 873021 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.4163. Min Act: -0.1700
Data Index: 4971079 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.3538. Min Act: -0.1700
Data Index: 5025739 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.3538. Min Act: -0.1700
Data Index: 193863 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.3538. Min Act: -0.1700
Data Index: 7087007 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.3538. Min Act: -0.1700
Data Index: 847349 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.2913. Min Act: -0.1700
Data Index: 1805042 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.3226. Min Act: -0.1700
Data Index: 5080456 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.3226. Min Act: -0.1700
Data Index: 8331351 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.2913. Min Act: -0.1700
Data Index: 1799360 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.2913. Min Act: -0.1700
Data Index: 6819690 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.2913. Min Act: -0.1700
Data Index: 6191527 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.2913. Min Act: -0.1700
Data Index: 3276123 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.3226. Min Act: -0.1700
Data Index: 2016960 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5726. Min Range: -5.5726
Max Act: 5.2913. Min Act: -0.1700
Data Index: 1804143 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19