Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2474 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8270. Min Range: -6.8270
Max Act: 6.8270. Min Act: -0.1700
Data Index: 2189389 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8270. Min Range: -6.8270
Max Act: 6.6707. Min Act: -0.1700
Data Index: 8100827 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8270. Min Range: -6.8270
Max Act: 6.4832. Min Act: -0.1700
Data Index: 2502440 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8270. Min Range: -6.8270
Max Act: 6.3895. Min Act: -0.1700
Data Index: 2584587 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8270. Min Range: -6.8270
Max Act: 6.3582. Min Act: -0.1700
Data Index: 6548615 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8270. Min Range: -6.8270
Max Act: 6.2645. Min Act: -0.1700
Data Index: 2698655 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8270. Min Range: -6.8270
Max Act: 6.2332. Min Act: -0.1700
Data Index: 8430386 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8270. Min Range: -6.8270
Max Act: 6.2020. Min Act: -0.1700
Data Index: 6736914 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8270. Min Range: -6.8270
Max Act: 6.1082. Min Act: -0.1700
Data Index: 6150480 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8270. Min Range: -6.8270
Max Act: 6.0457. Min Act: -0.1700
Data Index: 4235264 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8270. Min Range: -6.8270
Max Act: 6.0457. Min Act: -0.1700
Data Index: 390069 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8270. Min Range: -6.8270
Max Act: 6.0457. Min Act: -0.1700
Data Index: 6528730 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8270. Min Range: -6.8270
Max Act: 6.0770. Min Act: -0.1700
Data Index: 2555371 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8270. Min Range: -6.8270
Max Act: 6.0457. Min Act: -0.1700
Data Index: 7105838 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8270. Min Range: -6.8270
Max Act: 6.0145. Min Act: -0.1700
Data Index: 6544456 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8270. Min Range: -6.8270
Max Act: 6.0145. Min Act: -0.1700
Data Index: 1362636 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8270. Min Range: -6.8270
Max Act: 5.9520. Min Act: -0.1700
Data Index: 6239454 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8270. Min Range: -6.8270
Max Act: 5.9832. Min Act: -0.1700
Data Index: 1706744 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8270. Min Range: -6.8270
Max Act: 5.9207. Min Act: -0.1700
Data Index: 5889285 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8270. Min Range: -6.8270
Max Act: 5.9520. Min Act: -0.1700
Data Index: 2730605 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19