Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3761 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.2399. Min Act: -0.1700
Data Index: 6887259 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.2399. Min Act: -0.1700
Data Index: 1113895 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.2087. Min Act: -0.1700
Data Index: 4041546 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.1774. Min Act: -0.1700
Data Index: 1671853 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.2087. Min Act: -0.1700
Data Index: 7981751 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.1462. Min Act: -0.1700
Data Index: 708731 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.1774. Min Act: -0.1700
Data Index: 1930037 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.1149. Min Act: -0.1700
Data Index: 7997812 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.1462. Min Act: -0.1700
Data Index: 6706885 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.1462. Min Act: -0.1700
Data Index: 6479121 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.1149. Min Act: -0.1700
Data Index: 2194792 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.1149. Min Act: -0.1700
Data Index: 7796500 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.1462. Min Act: -0.1700
Data Index: 7435796 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.1149. Min Act: -0.1700
Data Index: 5059780 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.0524. Min Act: -0.1700
Data Index: 7608191 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.1149. Min Act: -0.1700
Data Index: 3471839 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.0212. Min Act: -0.1700
Data Index: 327207 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.0524. Min Act: -0.1700
Data Index: 8587442 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2399. Min Range: -6.2399
Max Act: 6.0212. Min Act: -0.1700
Data Index: 661711 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2399. Min Range: -6.2399
Max Act: 5.9899. Min Act: -0.1700
Data Index: 4455984 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19