Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2477 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.8999. Min Act: -0.1700
Data Index: 4870944 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.8999. Min Act: -0.1700
Data Index: 1180 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.9624. Min Act: -0.1700
Data Index: 5614107 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.7124. Min Act: -0.1700
Data Index: 2214874 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.5249. Min Act: -0.1700
Data Index: 4393441 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.5562. Min Act: -0.1700
Data Index: 2195922 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.4937. Min Act: -0.1700
Data Index: 4113332 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.3687. Min Act: -0.1681
Data Index: 3653677 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.4624. Min Act: -0.1700
Data Index: 536754 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.4937. Min Act: -0.1700
Data Index: 2665953 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.3687. Min Act: -0.1700
Data Index: 69037 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.4312. Min Act: -0.1700
Data Index: 4310464 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.3374. Min Act: -0.1700
Data Index: 5403693 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.3999. Min Act: -0.1700
Data Index: 4311413 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.3374. Min Act: -0.1700
Data Index: 2400370 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.3374. Min Act: -0.1692
Data Index: 5299319 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.4312. Min Act: -0.1700
Data Index: 2665950 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.3062. Min Act: -0.1700
Data Index: 2400371 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.3374. Min Act: -0.1700
Data Index: 6023288 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9624. Min Range: -7.9624
Max Act: 7.3062. Min Act: -0.1700
Data Index: 4701216 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19