Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4123. Min Range: -8.4123
Max Act: 8.4123. Min Act: -0.1700
Data Index: 7570234 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4123. Min Range: -8.4123
Max Act: 8.2873. Min Act: -0.1700
Data Index: 1065498 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4123. Min Range: -8.4123
Max Act: 8.2248. Min Act: -0.1700
Data Index: 6649824 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4123. Min Range: -8.4123
Max Act: 8.0998. Min Act: -0.1700
Data Index: 4259255 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4123. Min Range: -8.4123
Max Act: 8.0998. Min Act: -0.1700
Data Index: 5321499 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4123. Min Range: -8.4123
Max Act: 7.9748. Min Act: -0.1700
Data Index: 8742146 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4123. Min Range: -8.4123
Max Act: 8.0373. Min Act: -0.1700
Data Index: 5745814 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4123. Min Range: -8.4123
Max Act: 8.0373. Min Act: -0.1700
Data Index: 5879301 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4123. Min Range: -8.4123
Max Act: 7.9748. Min Act: -0.1700
Data Index: 3669121 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4123. Min Range: -8.4123
Max Act: 7.9123. Min Act: -0.1700
Data Index: 3585952 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4123. Min Range: -8.4123
Max Act: 7.9123. Min Act: -0.1700
Data Index: 8535415 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4123. Min Range: -8.4123
Max Act: 7.9748. Min Act: -0.1700
Data Index: 7106481 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4123. Min Range: -8.4123
Max Act: 7.9748. Min Act: -0.1700
Data Index: 7401298 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4123. Min Range: -8.4123
Max Act: 7.9123. Min Act: -0.1700
Data Index: 6795028 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4123. Min Range: -8.4123
Max Act: 7.9123. Min Act: -0.1700
Data Index: 2371382 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4123. Min Range: -8.4123
Max Act: 7.9123. Min Act: -0.1700
Data Index: 2468609 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4123. Min Range: -8.4123
Max Act: 7.9748. Min Act: -0.1700
Data Index: 2484096 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4123. Min Range: -8.4123
Max Act: 7.7873. Min Act: -0.1700
Data Index: 6156862 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4123. Min Range: -8.4123
Max Act: 7.8498. Min Act: -0.1700
Data Index: 4295647 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4123. Min Range: -8.4123
Max Act: 7.8498. Min Act: -0.1700
Data Index: 4462018 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19