Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2984 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.8107. Min Act: -0.1700
Data Index: 4320281 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.7935. Min Act: -0.1700
Data Index: 6929500 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.7158. Min Act: -0.1700
Data Index: 2729530 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.6985. Min Act: -0.1700
Data Index: 7662354 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.6898. Min Act: -0.1700
Data Index: 4578980 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.6637. Min Act: -0.1700
Data Index: 1073590 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.6724. Min Act: -0.1700
Data Index: 931019 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.6811. Min Act: -0.1700
Data Index: 7590050 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.6637. Min Act: -0.1700
Data Index: 4706569 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.6637. Min Act: -0.1700
Data Index: 6624217 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.6724. Min Act: -0.1700
Data Index: 560132 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.6550. Min Act: -0.1700
Data Index: 8240627 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.6637. Min Act: -0.1700
Data Index: 5803760 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.6550. Min Act: -0.1700
Data Index: 1481437 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.6550. Min Act: -0.1700
Data Index: 7880462 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.6463. Min Act: -0.1700
Data Index: 738677 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.6376. Min Act: -0.1700
Data Index: 7277613 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.6289. Min Act: -0.1700
Data Index: 7360480 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.6550. Min Act: -0.1700
Data Index: 560133 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8107. Min Range: -1.8107
Max Act: 1.6376. Min Act: -0.1700
Data Index: 5947752 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19