Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3443 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7378. Min Range: -8.7378
Max Act: 8.7378. Min Act: -0.1700
Data Index: 8796926 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7378. Min Range: -8.7378
Max Act: 8.3628. Min Act: -0.1700
Data Index: 8538197 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7378. Min Range: -8.7378
Max Act: 8.3628. Min Act: -0.1700
Data Index: 597253 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7378. Min Range: -8.7378
Max Act: 8.3003. Min Act: -0.1700
Data Index: 7928719 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7378. Min Range: -8.7378
Max Act: 8.1753. Min Act: -0.1700
Data Index: 187311 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7378. Min Range: -8.7378
Max Act: 8.1753. Min Act: -0.1700
Data Index: 70208 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7378. Min Range: -8.7378
Max Act: 8.1753. Min Act: -0.1700
Data Index: 2010367 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7378. Min Range: -8.7378
Max Act: 8.1753. Min Act: -0.1700
Data Index: 8561211 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7378. Min Range: -8.7378
Max Act: 8.1128. Min Act: -0.1700
Data Index: 339461 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7378. Min Range: -8.7378
Max Act: 8.0503. Min Act: -0.1700
Data Index: 8745218 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7378. Min Range: -8.7378
Max Act: 8.0503. Min Act: -0.1700
Data Index: 5495833 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7378. Min Range: -8.7378
Max Act: 8.0503. Min Act: -0.1700
Data Index: 2931398 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7378. Min Range: -8.7378
Max Act: 7.9878. Min Act: -0.1700
Data Index: 3199381 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7378. Min Range: -8.7378
Max Act: 8.0503. Min Act: -0.1700
Data Index: 1604750 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7378. Min Range: -8.7378
Max Act: 7.9878. Min Act: -0.1700
Data Index: 845552 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7378. Min Range: -8.7378
Max Act: 7.9253. Min Act: -0.1700
Data Index: 4228343 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7378. Min Range: -8.7378
Max Act: 7.9253. Min Act: -0.1700
Data Index: 2832988 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7378. Min Range: -8.7378
Max Act: 7.9253. Min Act: -0.1700
Data Index: 6729919 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7378. Min Range: -8.7378
Max Act: 7.8628. Min Act: -0.1700
Data Index: 4108392 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7378. Min Range: -8.7378
Max Act: 7.8315. Min Act: -0.1700
Data Index: 3283239 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19