Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2613 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.0694. Min Range: -1.0694
Max Act: 1.0694. Min Act: -0.1700
Data Index: 6509685 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0694. Min Range: -1.0694
Max Act: 1.0171. Min Act: -0.1700
Data Index: 1725521 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0694. Min Range: -1.0694
Max Act: 0.9997. Min Act: -0.1700
Data Index: 967015 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0694. Min Range: -1.0694
Max Act: 0.9824. Min Act: -0.1699
Data Index: 1667573 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0694. Min Range: -1.0694
Max Act: 0.9651. Min Act: -0.1700
Data Index: 6273205 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0694. Min Range: -1.0694
Max Act: 0.9824. Min Act: -0.1700
Data Index: 7017952 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0694. Min Range: -1.0694
Max Act: 0.9392. Min Act: -0.1700
Data Index: 381992 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0694. Min Range: -1.0694
Max Act: 0.9306. Min Act: -0.1698
Data Index: 3011207 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0694. Min Range: -1.0694
Max Act: 0.9134. Min Act: -0.1700
Data Index: 7020919 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0694. Min Range: -1.0694
Max Act: 0.9306. Min Act: -0.1700
Data Index: 1388932 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0694. Min Range: -1.0694
Max Act: 0.8963. Min Act: -0.1699
Data Index: 6967226 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0694. Min Range: -1.0694
Max Act: 0.8792. Min Act: -0.1700
Data Index: 3833936 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0694. Min Range: -1.0694
Max Act: 0.8792. Min Act: -0.1691
Data Index: 7545870 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0694. Min Range: -1.0694
Max Act: 0.8878. Min Act: -0.1696
Data Index: 4444251 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0694. Min Range: -1.0694
Max Act: 0.8792. Min Act: -0.1700
Data Index: 5528783 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0694. Min Range: -1.0694
Max Act: 0.8792. Min Act: -0.1700
Data Index: 3455132 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0694. Min Range: -1.0694
Max Act: 0.8878. Min Act: -0.1700
Data Index: 6945723 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0694. Min Range: -1.0694
Max Act: 0.8707. Min Act: -0.1700
Data Index: 989066 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0694. Min Range: -1.0694
Max Act: 0.8622. Min Act: -0.1700
Data Index: 8340134 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0694. Min Range: -1.0694
Max Act: 0.8537. Min Act: -0.1700
Data Index: 8297097 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19