Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2011 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.7325. Min Act: -0.1700
Data Index: 7925777 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.2012. Min Act: -0.1700
Data Index: 4252478 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.1387. Min Act: -0.1700
Data Index: 3627195 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.1700. Min Act: -0.1700
Data Index: 6971563 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.1387. Min Act: -0.1700
Data Index: 5579290 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.0762. Min Act: -0.1700
Data Index: 3800009 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.0450. Min Act: -0.1700
Data Index: 7564218 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.0450. Min Act: -0.1700
Data Index: 6264335 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7325. Min Range: -6.7325
Max Act: 5.9825. Min Act: -0.1700
Data Index: 3084400 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7325. Min Range: -6.7325
Max Act: 5.9825. Min Act: -0.1700
Data Index: 8776923 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7325. Min Range: -6.7325
Max Act: 5.9200. Min Act: -0.1700
Data Index: 2923104 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7325. Min Range: -6.7325
Max Act: 5.9200. Min Act: -0.1700
Data Index: 4759384 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7325. Min Range: -6.7325
Max Act: 5.9512. Min Act: -0.1700
Data Index: 8223863 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7325. Min Range: -6.7325
Max Act: 5.9200. Min Act: -0.1700
Data Index: 4788011 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7325. Min Range: -6.7325
Max Act: 5.9200. Min Act: -0.1700
Data Index: 1697596 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7325. Min Range: -6.7325
Max Act: 5.9200. Min Act: -0.1700
Data Index: 8776924 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7325. Min Range: -6.7325
Max Act: 5.8887. Min Act: -0.1700
Data Index: 6648456 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7325. Min Range: -6.7325
Max Act: 5.8887. Min Act: -0.1700
Data Index: 7889094 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7325. Min Range: -6.7325
Max Act: 5.8887. Min Act: -0.1700
Data Index: 5525709 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7325. Min Range: -6.7325
Max Act: 5.8575. Min Act: -0.1700
Data Index: 3387601 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19