Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3629 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.9033. Min Act: -0.1700
Data Index: 3900094 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.7158. Min Act: -0.1700
Data Index: 1921862 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.5283. Min Act: -0.1700
Data Index: 5032562 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.5908. Min Act: -0.1700
Data Index: 8224664 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.5908. Min Act: -0.1698
Data Index: 3062535 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.4658. Min Act: -0.1698
Data Index: 6028627 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.5283. Min Act: -0.1700
Data Index: 7384255 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.4658. Min Act: -0.1700
Data Index: 258686 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.5283. Min Act: -0.1700
Data Index: 7805886 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.4033. Min Act: -0.1700
Data Index: 998360 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.4033. Min Act: -0.1700
Data Index: 7188240 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.4033. Min Act: -0.1700
Data Index: 2884433 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.3408. Min Act: -0.1698
Data Index: 694444 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.4033. Min Act: -0.1700
Data Index: 1561442 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.3408. Min Act: -0.1700
Data Index: 3563473 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.3408. Min Act: -0.1700
Data Index: 4443549 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.3408. Min Act: -0.1700
Data Index: 344901 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.3408. Min Act: -0.1699
Data Index: 2969324 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.2783. Min Act: -0.1700
Data Index: 3265971 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9033. Min Range: -8.9033
Max Act: 8.2158. Min Act: -0.1700
Data Index: 6835102 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19