Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 990 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.4306. Min Act: -0.1700
Data Index: 100779 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.4306. Min Act: -0.1700
Data Index: 2035236 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.2743. Min Act: -0.1700
Data Index: 3347956 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.2118. Min Act: -0.1700
Data Index: 4125557 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.2118. Min Act: -0.1700
Data Index: 2013374 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.2118. Min Act: -0.1700
Data Index: 3376474 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.1806. Min Act: -0.1700
Data Index: 4256046 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.1493. Min Act: -0.1700
Data Index: 6549702 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.1493. Min Act: -0.1700
Data Index: 4321164 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.1493. Min Act: -0.1700
Data Index: 1275634 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.1806. Min Act: -0.1700
Data Index: 8655038 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.1493. Min Act: -0.1700
Data Index: 3703712 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.1180. Min Act: -0.1700
Data Index: 2445419 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.1180. Min Act: -0.1700
Data Index: 4880990 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.1180. Min Act: -0.1700
Data Index: 4325863 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.0868. Min Act: -0.1700
Data Index: 1468860 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.1180. Min Act: -0.1700
Data Index: 5406707 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.0868. Min Act: -0.1700
Data Index: 428054 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.0868. Min Act: -0.1700
Data Index: 4748668 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4306. Min Range: -4.4306
Max Act: 4.0868. Min Act: -0.1700
Data Index: 6334381 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19