Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2975 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.8736. Min Act: -0.1700
Data Index: 2487228 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.8423. Min Act: -0.1700
Data Index: 5620270 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.8111. Min Act: -0.1700
Data Index: 2937871 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.8111. Min Act: -0.1700
Data Index: 2109378 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.7173. Min Act: -0.1700
Data Index: 7139191 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.7173. Min Act: -0.1700
Data Index: 8371498 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.6548. Min Act: -0.1700
Data Index: 2109381 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.5611. Min Act: -0.1700
Data Index: 389816 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.4986. Min Act: -0.1700
Data Index: 2251531 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.5298. Min Act: -0.1700
Data Index: 1237471 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.4986. Min Act: -0.1700
Data Index: 7467412 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.4361. Min Act: -0.1700
Data Index: 3630012 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.4673. Min Act: -0.1700
Data Index: 3832871 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.4986. Min Act: -0.1700
Data Index: 1618872 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.4048. Min Act: -0.1700
Data Index: 990701 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.4048. Min Act: -0.1700
Data Index: 3817139 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.3111. Min Act: -0.1700
Data Index: 5869389 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.2798. Min Act: -0.1700
Data Index: 1618870 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.3111. Min Act: -0.1700
Data Index: 5245326 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.3111. Min Act: -0.1700
Data Index: 4361956 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19