Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2426 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2240. Min Range: -8.2240
Max Act: 8.2240. Min Act: -0.1700
Data Index: 5625594 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.5365. Min Act: -0.1700
Data Index: 6318142 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.5678. Min Act: -0.1700
Data Index: 8257423 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.4428. Min Act: -0.1700
Data Index: 5059006 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.4428. Min Act: -0.1700
Data Index: 7075214 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.3490. Min Act: -0.1700
Data Index: 4442492 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.3803. Min Act: -0.1700
Data Index: 5513607 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.3178. Min Act: -0.1700
Data Index: 4612683 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.1928. Min Act: -0.1700
Data Index: 4081341 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.2865. Min Act: -0.1700
Data Index: 1849988 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.3490. Min Act: -0.1700
Data Index: 2036907 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.2553. Min Act: -0.1700
Data Index: 8159966 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.2553. Min Act: -0.1700
Data Index: 6133167 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.2553. Min Act: -0.1700
Data Index: 1278288 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.2240. Min Act: -0.1700
Data Index: 5428978 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.2553. Min Act: -0.1700
Data Index: 7166137 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.1928. Min Act: -0.1700
Data Index: 27386 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.1928. Min Act: -0.1700
Data Index: 2442474 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.1615. Min Act: -0.1700
Data Index: 1500979 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2240. Min Range: -8.2240
Max Act: 7.1928. Min Act: -0.1700
Data Index: 7764798 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19