Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1000 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4502. Min Range: -8.4502
Max Act: 8.4502. Min Act: -0.1700
Data Index: 3184812 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.8877. Min Act: -0.1700
Data Index: 7314156 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.8565. Min Act: -0.1700
Data Index: 4341792 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.8565. Min Act: -0.1700
Data Index: 1704448 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.7315. Min Act: -0.1700
Data Index: 4928216 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.6690. Min Act: -0.1700
Data Index: 7858137 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.6065. Min Act: -0.1700
Data Index: 5573572 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.6377. Min Act: -0.1700
Data Index: 1806542 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.5752. Min Act: -0.1700
Data Index: 4295315 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.5440. Min Act: -0.1700
Data Index: 155214 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.5127. Min Act: -0.1700
Data Index: 6600522 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.4815. Min Act: -0.1700
Data Index: 8524797 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.5127. Min Act: -0.1700
Data Index: 256955 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.4190. Min Act: -0.1700
Data Index: 1879526 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.5127. Min Act: -0.1700
Data Index: 3205384 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.4815. Min Act: -0.1700
Data Index: 4388725 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.4502. Min Act: -0.1700
Data Index: 6977439 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.4502. Min Act: -0.1700
Data Index: 3350425 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.4502. Min Act: -0.1700
Data Index: 6151819 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4502. Min Range: -8.4502
Max Act: 7.4190. Min Act: -0.1700
Data Index: 7030760 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19