Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 491 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7596. Min Range: -6.7596
Max Act: 6.7596. Min Act: -0.1700
Data Index: 8121713 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7596. Min Range: -6.7596
Max Act: 6.1034. Min Act: -0.1700
Data Index: 7915052 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7596. Min Range: -6.7596
Max Act: 6.1034. Min Act: -0.1700
Data Index: 2407665 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7596. Min Range: -6.7596
Max Act: 6.0096. Min Act: -0.1700
Data Index: 3560922 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7596. Min Range: -6.7596
Max Act: 5.9471. Min Act: -0.1700
Data Index: 1206283 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7596. Min Range: -6.7596
Max Act: 5.9784. Min Act: -0.1700
Data Index: 2876758 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7596. Min Range: -6.7596
Max Act: 5.9784. Min Act: -0.1700
Data Index: 6856843 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7596. Min Range: -6.7596
Max Act: 5.9471. Min Act: -0.1700
Data Index: 8645870 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7596. Min Range: -6.7596
Max Act: 5.9159. Min Act: -0.1700
Data Index: 367356 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7596. Min Range: -6.7596
Max Act: 5.9159. Min Act: -0.1700
Data Index: 5303935 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7596. Min Range: -6.7596
Max Act: 5.8846. Min Act: -0.1700
Data Index: 3802984 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7596. Min Range: -6.7596
Max Act: 5.8534. Min Act: -0.1700
Data Index: 5558970 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7596. Min Range: -6.7596
Max Act: 5.8534. Min Act: -0.1700
Data Index: 5022298 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7596. Min Range: -6.7596
Max Act: 5.8534. Min Act: -0.1700
Data Index: 6047834 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7596. Min Range: -6.7596
Max Act: 5.8534. Min Act: -0.1700
Data Index: 4085430 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7596. Min Range: -6.7596
Max Act: 5.8534. Min Act: -0.1700
Data Index: 7750807 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7596. Min Range: -6.7596
Max Act: 5.8534. Min Act: -0.1700
Data Index: 5504789 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7596. Min Range: -6.7596
Max Act: 5.7596. Min Act: -0.1700
Data Index: 6569755 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7596. Min Range: -6.7596
Max Act: 5.7596. Min Act: -0.1700
Data Index: 5495803 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7596. Min Range: -6.7596
Max Act: 5.7909. Min Act: -0.1700
Data Index: 3447382 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19