Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1872 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0320. Min Range: -6.0320
Max Act: 6.0320. Min Act: -0.1700
Data Index: 6760445 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.8445. Min Act: -0.1700
Data Index: 6761502 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.8133. Min Act: -0.1700
Data Index: 8364411 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.7195. Min Act: -0.1700
Data Index: 2536910 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.6883. Min Act: -0.1700
Data Index: 3147978 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.6570. Min Act: -0.1700
Data Index: 4362432 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.5945. Min Act: -0.1700
Data Index: 7919813 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.5945. Min Act: -0.1700
Data Index: 5090039 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.5633. Min Act: -0.1700
Data Index: 5802072 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.5320. Min Act: -0.1700
Data Index: 309234 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.5320. Min Act: -0.1700
Data Index: 4866715 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.5320. Min Act: -0.1700
Data Index: 2947781 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.5008. Min Act: -0.1700
Data Index: 3267115 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.5320. Min Act: -0.1700
Data Index: 185518 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.5008. Min Act: -0.1700
Data Index: 7073334 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.4695. Min Act: -0.1700
Data Index: 7853121 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.4695. Min Act: -0.1700
Data Index: 4032195 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.4695. Min Act: -0.1700
Data Index: 4097683 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.4383. Min Act: -0.1700
Data Index: 8144206 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0320. Min Range: -6.0320
Max Act: 5.4695. Min Act: -0.1700
Data Index: 5159839 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19