Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2664 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3404. Min Range: -6.3404
Max Act: 6.3404. Min Act: -0.1700
Data Index: 7883810 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3404. Min Range: -6.3404
Max Act: 6.3091. Min Act: -0.1700
Data Index: 6994234 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3404. Min Range: -6.3404
Max Act: 6.2779. Min Act: -0.1700
Data Index: 5505527 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3404. Min Range: -6.3404
Max Act: 6.2154. Min Act: -0.1700
Data Index: 902889 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3404. Min Range: -6.3404
Max Act: 6.1841. Min Act: -0.1700
Data Index: 2637282 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3404. Min Range: -6.3404
Max Act: 6.1529. Min Act: -0.1700
Data Index: 381026 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3404. Min Range: -6.3404
Max Act: 6.1216. Min Act: -0.1700
Data Index: 8693461 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3404. Min Range: -6.3404
Max Act: 6.1216. Min Act: -0.1700
Data Index: 648157 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3404. Min Range: -6.3404
Max Act: 6.1529. Min Act: -0.1700
Data Index: 1225278 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3404. Min Range: -6.3404
Max Act: 6.0904. Min Act: -0.1700
Data Index: 2435187 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3404. Min Range: -6.3404
Max Act: 6.0591. Min Act: -0.1700
Data Index: 6578984 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3404. Min Range: -6.3404
Max Act: 6.0591. Min Act: -0.1700
Data Index: 4196710 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3404. Min Range: -6.3404
Max Act: 6.0591. Min Act: -0.1700
Data Index: 7652463 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3404. Min Range: -6.3404
Max Act: 6.0591. Min Act: -0.1700
Data Index: 5230738 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3404. Min Range: -6.3404
Max Act: 6.0279. Min Act: -0.1700
Data Index: 5051295 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3404. Min Range: -6.3404
Max Act: 6.0279. Min Act: -0.1700
Data Index: 183362 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3404. Min Range: -6.3404
Max Act: 5.9966. Min Act: -0.1700
Data Index: 6298394 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3404. Min Range: -6.3404
Max Act: 5.9654. Min Act: -0.1700
Data Index: 4140670 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3404. Min Range: -6.3404
Max Act: 5.9341. Min Act: -0.1700
Data Index: 6217404 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3404. Min Range: -6.3404
Max Act: 5.9341. Min Act: -0.1700
Data Index: 1482773 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19