Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1088 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.9658. Min Act: -0.1700
Data Index: 2285389 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.6221. Min Act: -0.1700
Data Index: 5275039 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.6221. Min Act: -0.1700
Data Index: 8177333 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.5596. Min Act: -0.1700
Data Index: 474128 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.4658. Min Act: -0.1700
Data Index: 7124060 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.4971. Min Act: -0.1700
Data Index: 1097311 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.4346. Min Act: -0.1700
Data Index: 8457588 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.4658. Min Act: -0.1700
Data Index: 885828 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.4658. Min Act: -0.1700
Data Index: 7352764 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.4658. Min Act: -0.1700
Data Index: 747624 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.4346. Min Act: -0.1700
Data Index: 319338 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.4346. Min Act: -0.1700
Data Index: 3491096 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.4346. Min Act: -0.1700
Data Index: 1336386 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.4033. Min Act: -0.1700
Data Index: 5923950 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.3721. Min Act: -0.1700
Data Index: 6667516 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.3096. Min Act: -0.1700
Data Index: 6921441 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.3096. Min Act: -0.1700
Data Index: 2871264 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.2783. Min Act: -0.1700
Data Index: 4527316 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.2783. Min Act: -0.1700
Data Index: 1806668 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9658. Min Range: -5.9658
Max Act: 5.2471. Min Act: -0.1700
Data Index: 885827 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19