Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2448 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7411. Min Range: -8.7411
Max Act: 8.7411. Min Act: -0.1700
Data Index: 8592666 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7411. Min Range: -8.7411
Max Act: 8.2411. Min Act: -0.1700
Data Index: 5327036 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7411. Min Range: -8.7411
Max Act: 8.1786. Min Act: -0.1700
Data Index: 444354 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7411. Min Range: -8.7411
Max Act: 8.1786. Min Act: -0.1700
Data Index: 8332071 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7411. Min Range: -8.7411
Max Act: 8.1786. Min Act: -0.1700
Data Index: 4995423 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7411. Min Range: -8.7411
Max Act: 8.1161. Min Act: -0.1700
Data Index: 4650808 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7411. Min Range: -8.7411
Max Act: 8.0536. Min Act: -0.1700
Data Index: 7872660 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7411. Min Range: -8.7411
Max Act: 8.0536. Min Act: -0.1700
Data Index: 6377939 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7411. Min Range: -8.7411
Max Act: 8.0536. Min Act: -0.1700
Data Index: 7443577 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7411. Min Range: -8.7411
Max Act: 8.0536. Min Act: -0.1700
Data Index: 6222433 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7411. Min Range: -8.7411
Max Act: 8.1161. Min Act: -0.1700
Data Index: 86142 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7411. Min Range: -8.7411
Max Act: 7.9286. Min Act: -0.1700
Data Index: 63440 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7411. Min Range: -8.7411
Max Act: 7.9911. Min Act: -0.1700
Data Index: 4904755 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7411. Min Range: -8.7411
Max Act: 7.9286. Min Act: -0.1700
Data Index: 6294346 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7411. Min Range: -8.7411
Max Act: 7.9286. Min Act: -0.1700
Data Index: 6681563 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7411. Min Range: -8.7411
Max Act: 7.9286. Min Act: -0.1700
Data Index: 3036319 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7411. Min Range: -8.7411
Max Act: 7.8661. Min Act: -0.1700
Data Index: 4926223 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7411. Min Range: -8.7411
Max Act: 7.8661. Min Act: -0.1700
Data Index: 7624697 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7411. Min Range: -8.7411
Max Act: 7.8661. Min Act: -0.1700
Data Index: 414944 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7411. Min Range: -8.7411
Max Act: 7.8036. Min Act: -0.1700
Data Index: 5255710 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19