Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 38 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.4205. Min Act: -0.1700
Data Index: 6612323 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.3268. Min Act: -0.1700
Data Index: 3925657 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.3580. Min Act: -0.1700
Data Index: 6093258 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.2330. Min Act: -0.1700
Data Index: 5966428 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.2330. Min Act: -0.1700
Data Index: 3607550 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.2330. Min Act: -0.1700
Data Index: 2550722 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.2018. Min Act: -0.1700
Data Index: 6127811 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.2018. Min Act: -0.1700
Data Index: 6127671 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.2018. Min Act: -0.1700
Data Index: 3853130 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.2018. Min Act: -0.1700
Data Index: 4681464 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.1705. Min Act: -0.1700
Data Index: 3474323 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.1705. Min Act: -0.1700
Data Index: 5278433 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.1393. Min Act: -0.1700
Data Index: 6810366 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.2018. Min Act: -0.1700
Data Index: 1111697 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.1393. Min Act: -0.1700
Data Index: 1773834 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.1705. Min Act: -0.1700
Data Index: 4081981 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.1705. Min Act: -0.1700
Data Index: 6607170 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.1705. Min Act: -0.1700
Data Index: 937667 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.1705. Min Act: -0.1700
Data Index: 2695948 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4205. Min Range: -4.4205
Max Act: 4.2330. Min Act: -0.1700
Data Index: 2593743 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19