Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 39 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.4209. Min Act: -0.1700
Data Index: 4153099 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.2959. Min Act: -0.1700
Data Index: 4522034 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.2334. Min Act: -0.1700
Data Index: 2155230 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.2647. Min Act: -0.1700
Data Index: 2100580 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.2022. Min Act: -0.1700
Data Index: 1327768 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.2022. Min Act: -0.1700
Data Index: 3864365 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.2334. Min Act: -0.1700
Data Index: 4631725 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.1709. Min Act: -0.1700
Data Index: 2525466 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.1709. Min Act: -0.1700
Data Index: 3715890 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.1397. Min Act: -0.1700
Data Index: 4717569 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.0459. Min Act: -0.1700
Data Index: 1335247 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.0459. Min Act: -0.1700
Data Index: 6801214 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.0459. Min Act: -0.1700
Data Index: 8162426 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.0459. Min Act: -0.1700
Data Index: 3065722 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.0459. Min Act: -0.1700
Data Index: 1073595 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.0772. Min Act: -0.1700
Data Index: 7962905 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.0459. Min Act: -0.1700
Data Index: 5359011 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.0459. Min Act: -0.1700
Data Index: 2428670 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.0147. Min Act: -0.1700
Data Index: 6016316 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4209. Min Range: -6.4209
Max Act: 6.0147. Min Act: -0.1700
Data Index: 5626575 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19