Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2412. Min Range: -7.2412
Max Act: 7.2412. Min Act: -0.1700
Data Index: 4411486 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.9912. Min Act: -0.1700
Data Index: 1308314 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.9912. Min Act: -0.1700
Data Index: 42283 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.8975. Min Act: -0.1700
Data Index: 1431703 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.8975. Min Act: -0.1700
Data Index: 1263237 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.8037. Min Act: -0.1700
Data Index: 5289821 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.8037. Min Act: -0.1700
Data Index: 7674836 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.7412. Min Act: -0.1700
Data Index: 2812433 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.7412. Min Act: -0.1700
Data Index: 7501157 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.7412. Min Act: -0.1700
Data Index: 4086335 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.5537. Min Act: -0.1700
Data Index: 3628789 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.5225. Min Act: -0.1700
Data Index: 5538128 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.4912. Min Act: -0.1700
Data Index: 8452472 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.4912. Min Act: -0.1700
Data Index: 7256388 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.4600. Min Act: -0.1700
Data Index: 604022 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.3975. Min Act: -0.1700
Data Index: 4903475 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.3975. Min Act: -0.1700
Data Index: 6837460 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.3975. Min Act: -0.1700
Data Index: 6753374 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.3662. Min Act: -0.1700
Data Index: 1860683 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.4287. Min Act: -0.1700
Data Index: 698410 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19