Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2772 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.9737. Min Act: -0.1700
Data Index: 5837811 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.9228. Min Act: -0.1700
Data Index: 8576363 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.8887. Min Act: -0.1700
Data Index: 7817449 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.9057. Min Act: -0.1700
Data Index: 2091903 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.8887. Min Act: -0.1700
Data Index: 2558225 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.8887. Min Act: -0.1700
Data Index: 7666930 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.8887. Min Act: -0.1700
Data Index: 4394712 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.8716. Min Act: -0.1700
Data Index: 2275584 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.8716. Min Act: -0.1700
Data Index: 3755762 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.8716. Min Act: -0.1700
Data Index: 2091902 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.8545. Min Act: -0.1700
Data Index: 7500355 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.8545. Min Act: -0.1700
Data Index: 1125729 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.8373. Min Act: -0.1700
Data Index: 2417039 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.8373. Min Act: -0.1700
Data Index: 6207859 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.8545. Min Act: -0.1700
Data Index: 1701659 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.8373. Min Act: -0.1700
Data Index: 3629229 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.8373. Min Act: -0.1700
Data Index: 3469769 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.8373. Min Act: -0.1700
Data Index: 4365706 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.8030. Min Act: -0.1700
Data Index: 4928727 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9737. Min Range: -1.9737
Max Act: 1.8202. Min Act: -0.1700
Data Index: 5975061 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19