Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1829 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1255. Min Range: -6.1255
Max Act: 6.1255. Min Act: -0.1700
Data Index: 1203980 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.9693. Min Act: -0.1700
Data Index: 1377495 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.8755. Min Act: -0.1700
Data Index: 8440134 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.8755. Min Act: -0.1700
Data Index: 1184244 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.8443. Min Act: -0.1700
Data Index: 6756877 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.8130. Min Act: -0.1700
Data Index: 2445487 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.7193. Min Act: -0.1700
Data Index: 2866042 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.7193. Min Act: -0.1700
Data Index: 4168047 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.7193. Min Act: -0.1700
Data Index: 2660215 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.6880. Min Act: -0.1700
Data Index: 1362322 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.6568. Min Act: -0.1700
Data Index: 6933813 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.6255. Min Act: -0.1700
Data Index: 2683317 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.6255. Min Act: -0.1700
Data Index: 7344063 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.6568. Min Act: -0.1700
Data Index: 4570765 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.5943. Min Act: -0.1700
Data Index: 8278503 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.5630. Min Act: -0.1700
Data Index: 5557493 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.5630. Min Act: -0.1700
Data Index: 4138458 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.5318. Min Act: -0.1700
Data Index: 4757026 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.4693. Min Act: -0.1700
Data Index: 3500522 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.4693. Min Act: -0.1700
Data Index: 7142659 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19