Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 373 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.0484. Min Range: -10.0484
Max Act: 10.0484. Min Act: -0.1700
Data Index: 2128164 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0484. Min Range: -10.0484
Max Act: 10.0484. Min Act: -0.1700
Data Index: 381430 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0484. Min Range: -10.0484
Max Act: 9.9234. Min Act: -0.1700
Data Index: 4841947 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0484. Min Range: -10.0484
Max Act: 9.9234. Min Act: -0.1700
Data Index: 1158130 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0484. Min Range: -10.0484
Max Act: 9.7984. Min Act: -0.1700
Data Index: 250440 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0484. Min Range: -10.0484
Max Act: 9.6734. Min Act: -0.1700
Data Index: 5458647 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0484. Min Range: -10.0484
Max Act: 9.6734. Min Act: -0.1700
Data Index: 6364647 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0484. Min Range: -10.0484
Max Act: 9.6734. Min Act: -0.1700
Data Index: 7862538 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0484. Min Range: -10.0484
Max Act: 9.6734. Min Act: -0.1700
Data Index: 8765847 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0484. Min Range: -10.0484
Max Act: 9.5484. Min Act: -0.1700
Data Index: 7001067 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0484. Min Range: -10.0484
Max Act: 9.5484. Min Act: -0.1700
Data Index: 8441106 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0484. Min Range: -10.0484
Max Act: 9.4859. Min Act: -0.1700
Data Index: 4417919 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0484. Min Range: -10.0484
Max Act: 9.4859. Min Act: -0.1700
Data Index: 6980895 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0484. Min Range: -10.0484
Max Act: 9.4234. Min Act: -0.1700
Data Index: 6196050 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0484. Min Range: -10.0484
Max Act: 9.2984. Min Act: -0.1700
Data Index: 4158244 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0484. Min Range: -10.0484
Max Act: 9.4234. Min Act: -0.1700
Data Index: 4783844 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0484. Min Range: -10.0484
Max Act: 9.1734. Min Act: -0.1700
Data Index: 5009822 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0484. Min Range: -10.0484
Max Act: 9.1734. Min Act: -0.1700
Data Index: 3822569 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0484. Min Range: -10.0484
Max Act: 9.2984. Min Act: -0.1700
Data Index: 2585187 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0484. Min Range: -10.0484
Max Act: 9.1734. Min Act: -0.1700
Data Index: 6794964 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19