Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.5587. Min Act: -0.1700
Data Index: 1909685 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.4649. Min Act: -0.1700
Data Index: 6409620 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.4337. Min Act: -0.1700
Data Index: 1542008 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.3712. Min Act: -0.1700
Data Index: 397130 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.3399. Min Act: -0.1700
Data Index: 6837456 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.4024. Min Act: -0.1700
Data Index: 4341956 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.3399. Min Act: -0.1700
Data Index: 3571536 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.3399. Min Act: -0.1700
Data Index: 4437047 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.3399. Min Act: -0.1700
Data Index: 3711040 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.3399. Min Act: -0.1700
Data Index: 5321641 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.3087. Min Act: -0.1700
Data Index: 6613929 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.3087. Min Act: -0.1700
Data Index: 8479306 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.3087. Min Act: -0.1700
Data Index: 115986 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.2774. Min Act: -0.1700
Data Index: 4055309 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.2774. Min Act: -0.1700
Data Index: 5103321 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.2149. Min Act: -0.1700
Data Index: 4925284 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.2774. Min Act: -0.1700
Data Index: 690819 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.2149. Min Act: -0.1700
Data Index: 5451165 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.2462. Min Act: -0.1700
Data Index: 6595545 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5587. Min Range: -6.5587
Max Act: 6.2462. Min Act: -0.1700
Data Index: 5953692 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19