Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3103 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.9162. Min Act: -0.1700
Data Index: 5877695 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.8537. Min Act: -0.1700
Data Index: 7238701 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.8225. Min Act: -0.1700
Data Index: 431026 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.8225. Min Act: -0.1700
Data Index: 3143367 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.7600. Min Act: -0.1700
Data Index: 4046485 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.7287. Min Act: -0.1700
Data Index: 6953234 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.6975. Min Act: -0.1700
Data Index: 212936 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.6975. Min Act: -0.1700
Data Index: 2972574 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.6037. Min Act: -0.1700
Data Index: 181822 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.6037. Min Act: -0.1700
Data Index: 8578001 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.5725. Min Act: -0.1700
Data Index: 6703484 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.5100. Min Act: -0.1700
Data Index: 7348292 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.5100. Min Act: -0.1700
Data Index: 5053422 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.5100. Min Act: -0.1700
Data Index: 8794533 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.4787. Min Act: -0.1700
Data Index: 3319566 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.5100. Min Act: -0.1700
Data Index: 5064451 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.4475. Min Act: -0.1700
Data Index: 7517191 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.4162. Min Act: -0.1700
Data Index: 2766376 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.4162. Min Act: -0.1700
Data Index: 3225579 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9162. Min Range: -6.9162
Max Act: 6.4162. Min Act: -0.1700
Data Index: 6776264 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19