Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4035 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.4738. Min Act: -0.1700
Data Index: 8550474 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.3488. Min Act: -0.1700
Data Index: 3500798 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.3175. Min Act: -0.1700
Data Index: 2194015 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.3175. Min Act: -0.1700
Data Index: 532075 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.3175. Min Act: -0.1700
Data Index: 1336249 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.2550. Min Act: -0.1700
Data Index: 6785393 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.2550. Min Act: -0.1700
Data Index: 2088862 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.2238. Min Act: -0.1700
Data Index: 6236193 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.1925. Min Act: -0.1700
Data Index: 4413884 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.1613. Min Act: -0.1700
Data Index: 849905 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.1613. Min Act: -0.1700
Data Index: 4713824 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.1300. Min Act: -0.1700
Data Index: 3097633 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.0988. Min Act: -0.1700
Data Index: 37047 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.0988. Min Act: -0.1700
Data Index: 3959609 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.0988. Min Act: -0.1700
Data Index: 5870532 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.0988. Min Act: -0.1700
Data Index: 4255758 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.0988. Min Act: -0.1700
Data Index: 7841496 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.1300. Min Act: -0.1700
Data Index: 7004400 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.0675. Min Act: -0.1700
Data Index: 4376419 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4738. Min Range: -6.4738
Max Act: 6.0675. Min Act: -0.1700
Data Index: 5101308 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19