Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4901 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0427. Min Range: -7.0427
Max Act: 7.0427. Min Act: -0.1700
Data Index: 2963445 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.8239. Min Act: -0.1700
Data Index: 7748156 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.7614. Min Act: -0.1700
Data Index: 5496176 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.7302. Min Act: -0.1700
Data Index: 2112321 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.6989. Min Act: -0.1700
Data Index: 3497169 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.6677. Min Act: -0.1700
Data Index: 8760940 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.6364. Min Act: -0.1700
Data Index: 93823 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.6364. Min Act: -0.1700
Data Index: 4929455 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.5739. Min Act: -0.1700
Data Index: 2693682 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.6052. Min Act: -0.1700
Data Index: 8027296 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.6364. Min Act: -0.1700
Data Index: 3037806 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.5739. Min Act: -0.1700
Data Index: 4003745 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.5427. Min Act: -0.1700
Data Index: 1645997 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.5114. Min Act: -0.1700
Data Index: 856472 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.5114. Min Act: -0.1700
Data Index: 8403644 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.5114. Min Act: -0.1700
Data Index: 1552471 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.4802. Min Act: -0.1700
Data Index: 8161550 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.4802. Min Act: -0.1700
Data Index: 1748137 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.4489. Min Act: -0.1700
Data Index: 7276960 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0427. Min Range: -7.0427
Max Act: 6.4802. Min Act: -0.1700
Data Index: 2938026 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19