Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 188 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1975. Min Range: -7.1975
Max Act: 7.1975. Min Act: -0.1700
Data Index: 5861373 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1975. Min Range: -7.1975
Max Act: 7.0412. Min Act: -0.1700
Data Index: 5258685 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1975. Min Range: -7.1975
Max Act: 7.0725. Min Act: -0.1700
Data Index: 8127130 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1975. Min Range: -7.1975
Max Act: 6.9475. Min Act: -0.1700
Data Index: 7837889 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1975. Min Range: -7.1975
Max Act: 6.9475. Min Act: -0.1700
Data Index: 5977311 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1975. Min Range: -7.1975
Max Act: 6.6662. Min Act: -0.1700
Data Index: 292225 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1975. Min Range: -7.1975
Max Act: 6.6350. Min Act: -0.1700
Data Index: 4977631 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1975. Min Range: -7.1975
Max Act: 6.6662. Min Act: -0.1700
Data Index: 2534266 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1975. Min Range: -7.1975
Max Act: 6.6350. Min Act: -0.1700
Data Index: 1770615 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1975. Min Range: -7.1975
Max Act: 6.6350. Min Act: -0.1700
Data Index: 188456 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1975. Min Range: -7.1975
Max Act: 6.5412. Min Act: -0.1700
Data Index: 3818283 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1975. Min Range: -7.1975
Max Act: 6.4787. Min Act: -0.1700
Data Index: 5789352 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1975. Min Range: -7.1975
Max Act: 6.4475. Min Act: -0.1700
Data Index: 2222721 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1975. Min Range: -7.1975
Max Act: 6.4162. Min Act: -0.1700
Data Index: 7758055 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1975. Min Range: -7.1975
Max Act: 6.4162. Min Act: -0.1700
Data Index: 1659013 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1975. Min Range: -7.1975
Max Act: 6.3850. Min Act: -0.1700
Data Index: 961997 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1975. Min Range: -7.1975
Max Act: 6.3850. Min Act: -0.1700
Data Index: 4820857 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1975. Min Range: -7.1975
Max Act: 6.3537. Min Act: -0.1700
Data Index: 4945795 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1975. Min Range: -7.1975
Max Act: 6.3537. Min Act: -0.1700
Data Index: 6999378 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1975. Min Range: -7.1975
Max Act: 6.3537. Min Act: -0.1700
Data Index: 2898582 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19