Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2017 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.9834. Min Act: -0.1700
Data Index: 2197811 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.7959. Min Act: -0.1700
Data Index: 7486428 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.6709. Min Act: -0.1700
Data Index: 1020348 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.6709. Min Act: -0.1700
Data Index: 244891 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.6709. Min Act: -0.1700
Data Index: 6543924 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.6397. Min Act: -0.1700
Data Index: 2965890 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.6084. Min Act: -0.1700
Data Index: 5182318 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.5772. Min Act: -0.1700
Data Index: 8518137 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.5459. Min Act: -0.1700
Data Index: 8734874 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.5147. Min Act: -0.1700
Data Index: 8046739 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.5147. Min Act: -0.1700
Data Index: 2843363 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.4834. Min Act: -0.1700
Data Index: 5466186 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.4834. Min Act: -0.1700
Data Index: 2756619 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.4834. Min Act: -0.1700
Data Index: 6012319 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.4834. Min Act: -0.1700
Data Index: 5544699 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.4209. Min Act: -0.1700
Data Index: 4886297 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.4209. Min Act: -0.1700
Data Index: 4371318 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.4522. Min Act: -0.1700
Data Index: 2299309 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.4522. Min Act: -0.1700
Data Index: 4846372 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9834. Min Range: -5.9834
Max Act: 5.4522. Min Act: -0.1700
Data Index: 3091623 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19