Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2002 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.8592. Min Act: -0.1700
Data Index: 1142807 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.8421. Min Act: -0.1700
Data Index: 8272596 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.8421. Min Act: -0.1700
Data Index: 2477835 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.8421. Min Act: -0.1700
Data Index: 740479 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.8249. Min Act: -0.1700
Data Index: 6728446 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.8077. Min Act: -0.1700
Data Index: 2178791 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.8077. Min Act: -0.1700
Data Index: 5693855 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.8077. Min Act: -0.1700
Data Index: 6248487 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.7733. Min Act: -0.1700
Data Index: 6396318 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.7733. Min Act: -0.1700
Data Index: 6528770 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.7561. Min Act: -0.1700
Data Index: 7470178 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.7733. Min Act: -0.1700
Data Index: 8296430 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.7905. Min Act: -0.1700
Data Index: 461019 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.7388. Min Act: -0.1700
Data Index: 3370709 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.7561. Min Act: -0.1700
Data Index: 8488334 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.7388. Min Act: -0.1700
Data Index: 1876469 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.7561. Min Act: -0.1700
Data Index: 5745921 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.7561. Min Act: -0.1700
Data Index: 5677843 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.7561. Min Act: -0.1700
Data Index: 7514241 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8592. Min Range: -1.8592
Max Act: 1.7388. Min Act: -0.1700
Data Index: 5164182 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19