Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3833 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.1282. Min Range: -9.1282
Max Act: 9.1282. Min Act: -0.1700
Data Index: 3110868 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1282. Min Range: -9.1282
Max Act: 9.0032. Min Act: -0.1700
Data Index: 5415546 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1282. Min Range: -9.1282
Max Act: 9.0032. Min Act: -0.1700
Data Index: 7885542 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1282. Min Range: -9.1282
Max Act: 9.0032. Min Act: -0.1700
Data Index: 1479762 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1282. Min Range: -9.1282
Max Act: 8.9407. Min Act: -0.1700
Data Index: 6467459 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1282. Min Range: -9.1282
Max Act: 8.9407. Min Act: -0.1700
Data Index: 8795683 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1282. Min Range: -9.1282
Max Act: 8.8157. Min Act: -0.1700
Data Index: 3119932 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1282. Min Range: -9.1282
Max Act: 8.8157. Min Act: -0.1700
Data Index: 1729498 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1282. Min Range: -9.1282
Max Act: 8.8782. Min Act: -0.1700
Data Index: 516366 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1282. Min Range: -9.1282
Max Act: 8.8157. Min Act: -0.1700
Data Index: 5910885 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1282. Min Range: -9.1282
Max Act: 8.7532. Min Act: -0.1700
Data Index: 7956009 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1282. Min Range: -9.1282
Max Act: 8.8157. Min Act: -0.1700
Data Index: 4055525 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1282. Min Range: -9.1282
Max Act: 8.7532. Min Act: -0.1700
Data Index: 3132818 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1282. Min Range: -9.1282
Max Act: 8.7532. Min Act: -0.1700
Data Index: 7396639 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1282. Min Range: -9.1282
Max Act: 8.7532. Min Act: -0.1700
Data Index: 7341871 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1282. Min Range: -9.1282
Max Act: 8.7532. Min Act: -0.1700
Data Index: 3562312 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1282. Min Range: -9.1282
Max Act: 8.6907. Min Act: -0.1700
Data Index: 4729607 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1282. Min Range: -9.1282
Max Act: 8.6907. Min Act: -0.1700
Data Index: 130464 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1282. Min Range: -9.1282
Max Act: 8.6907. Min Act: -0.1700
Data Index: 609327 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1282. Min Range: -9.1282
Max Act: 8.6594. Min Act: -0.1700
Data Index: 6682840 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19