Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3348 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5308. Min Range: -6.5308
Max Act: 6.5308. Min Act: -0.1700
Data Index: 3836463 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5308. Min Range: -6.5308
Max Act: 6.2496. Min Act: -0.1700
Data Index: 345188 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5308. Min Range: -6.5308
Max Act: 6.2183. Min Act: -0.1700
Data Index: 6613377 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5308. Min Range: -6.5308
Max Act: 6.1558. Min Act: -0.1700
Data Index: 5922333 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5308. Min Range: -6.5308
Max Act: 6.1871. Min Act: -0.1700
Data Index: 3159427 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5308. Min Range: -6.5308
Max Act: 6.0933. Min Act: -0.1700
Data Index: 8153099 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5308. Min Range: -6.5308
Max Act: 6.0933. Min Act: -0.1700
Data Index: 6918822 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5308. Min Range: -6.5308
Max Act: 6.0933. Min Act: -0.1700
Data Index: 1992497 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5308. Min Range: -6.5308
Max Act: 6.0933. Min Act: -0.1700
Data Index: 8762436 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5308. Min Range: -6.5308
Max Act: 6.1246. Min Act: -0.1700
Data Index: 3791996 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5308. Min Range: -6.5308
Max Act: 6.0621. Min Act: -0.1700
Data Index: 2862840 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5308. Min Range: -6.5308
Max Act: 6.0621. Min Act: -0.1700
Data Index: 6670128 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5308. Min Range: -6.5308
Max Act: 6.0621. Min Act: -0.1700
Data Index: 6493521 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5308. Min Range: -6.5308
Max Act: 6.0621. Min Act: -0.1700
Data Index: 2236595 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5308. Min Range: -6.5308
Max Act: 6.0308. Min Act: -0.1700
Data Index: 645891 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5308. Min Range: -6.5308
Max Act: 6.0308. Min Act: -0.1700
Data Index: 3920444 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5308. Min Range: -6.5308
Max Act: 6.0308. Min Act: -0.1700
Data Index: 4082099 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5308. Min Range: -6.5308
Max Act: 6.0308. Min Act: -0.1700
Data Index: 399710 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5308. Min Range: -6.5308
Max Act: 5.9996. Min Act: -0.1700
Data Index: 479241 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5308. Min Range: -6.5308
Max Act: 5.9683. Min Act: -0.1700
Data Index: 2205565 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19