Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3044 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.4281. Min Act: -0.1700
Data Index: 2286379 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.3031. Min Act: -0.1700
Data Index: 2624992 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.2406. Min Act: -0.1700
Data Index: 7884977 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.2406. Min Act: -0.1700
Data Index: 7629392 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.2093. Min Act: -0.1700
Data Index: 7452007 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.1780. Min Act: -0.1700
Data Index: 6605256 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.2093. Min Act: -0.1700
Data Index: 352317 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.2093. Min Act: -0.1700
Data Index: 665805 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.1780. Min Act: -0.1700
Data Index: 2829117 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.1780. Min Act: -0.1700
Data Index: 2564086 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.1780. Min Act: -0.1700
Data Index: 8211933 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.2093. Min Act: -0.1700
Data Index: 1779722 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.1780. Min Act: -0.1700
Data Index: 7437776 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.1468. Min Act: -0.1700
Data Index: 958479 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.1780. Min Act: -0.1700
Data Index: 3685000 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.2093. Min Act: -0.1700
Data Index: 6718300 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.1780. Min Act: -0.1700
Data Index: 2703099 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.1780. Min Act: -0.1700
Data Index: 2003859 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.1780. Min Act: -0.1700
Data Index: 6294277 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4281. Min Range: -4.4281
Max Act: 4.1468. Min Act: -0.1700
Data Index: 5998338 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19