Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4592 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4989. Min Range: -5.4989
Max Act: 5.4989. Min Act: -0.1700
Data Index: 226956 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4989. Min Range: -5.4989
Max Act: 5.3114. Min Act: -0.1700
Data Index: 146699 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4989. Min Range: -5.4989
Max Act: 5.2802. Min Act: -0.1700
Data Index: 4401561 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4989. Min Range: -5.4989
Max Act: 5.2489. Min Act: -0.1700
Data Index: 850341 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4989. Min Range: -5.4989
Max Act: 5.1552. Min Act: -0.1700
Data Index: 552459 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4989. Min Range: -5.4989
Max Act: 5.1239. Min Act: -0.1700
Data Index: 8296919 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4989. Min Range: -5.4989
Max Act: 5.1239. Min Act: -0.1700
Data Index: 3909219 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4989. Min Range: -5.4989
Max Act: 5.0302. Min Act: -0.1700
Data Index: 7876469 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4989. Min Range: -5.4989
Max Act: 5.0614. Min Act: -0.1700
Data Index: 341213 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4989. Min Range: -5.4989
Max Act: 5.0614. Min Act: -0.1700
Data Index: 1089396 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4989. Min Range: -5.4989
Max Act: 5.0614. Min Act: -0.1700
Data Index: 6384719 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4989. Min Range: -5.4989
Max Act: 5.0302. Min Act: -0.1700
Data Index: 1633674 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4989. Min Range: -5.4989
Max Act: 5.0302. Min Act: -0.1700
Data Index: 2517243 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4989. Min Range: -5.4989
Max Act: 5.0302. Min Act: -0.1700
Data Index: 7255366 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4989. Min Range: -5.4989
Max Act: 4.9989. Min Act: -0.1700
Data Index: 7363664 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4989. Min Range: -5.4989
Max Act: 4.9989. Min Act: -0.1700
Data Index: 3598227 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4989. Min Range: -5.4989
Max Act: 4.9989. Min Act: -0.1700
Data Index: 8486408 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4989. Min Range: -5.4989
Max Act: 4.9677. Min Act: -0.1700
Data Index: 872172 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4989. Min Range: -5.4989
Max Act: 4.9677. Min Act: -0.1700
Data Index: 4681745 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4989. Min Range: -5.4989
Max Act: 4.9677. Min Act: -0.1700
Data Index: 525903 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19