Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1073 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.9222. Min Act: -0.1700
Data Index: 644797 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.6722. Min Act: -0.1700
Data Index: 1356099 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.6722. Min Act: -0.1700
Data Index: 4369917 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.6410. Min Act: -0.1700
Data Index: 7230021 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.6097. Min Act: -0.1700
Data Index: 3968932 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.5472. Min Act: -0.1700
Data Index: 1599286 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.5160. Min Act: -0.1700
Data Index: 2252013 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.4847. Min Act: -0.1700
Data Index: 2062310 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.4222. Min Act: -0.1700
Data Index: 3689106 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.4222. Min Act: -0.1700
Data Index: 6442097 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.3910. Min Act: -0.1700
Data Index: 3140722 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.3285. Min Act: -0.1700
Data Index: 5600603 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.2972. Min Act: -0.1700
Data Index: 6136253 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.2347. Min Act: -0.1700
Data Index: 3571384 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.2347. Min Act: -0.1700
Data Index: 7923683 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.2347. Min Act: -0.1700
Data Index: 1804536 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.2035. Min Act: -0.1700
Data Index: 5369103 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.1097. Min Act: -0.1700
Data Index: 2815517 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.1410. Min Act: -0.1700
Data Index: 676192 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9222. Min Range: -7.9222
Max Act: 7.1097. Min Act: -0.1700
Data Index: 1108951 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19