Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3135 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.6737. Min Act: -0.1699
Data Index: 5383677 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.6563. Min Act: -0.1700
Data Index: 5223780 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.6476. Min Act: -0.1700
Data Index: 8616128 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.6476. Min Act: -0.1700
Data Index: 4130015 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.6302. Min Act: -0.1700
Data Index: 3040686 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.6302. Min Act: -0.1700
Data Index: 517283 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.6127. Min Act: -0.1700
Data Index: 1143764 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.6127. Min Act: -0.1700
Data Index: 3114609 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.5865. Min Act: -0.1700
Data Index: 1670557 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.5865. Min Act: -0.1700
Data Index: 4322232 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.5953. Min Act: -0.1700
Data Index: 8238481 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.6040. Min Act: -0.1700
Data Index: 5399213 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.5865. Min Act: -0.1700
Data Index: 8112317 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.5778. Min Act: -0.1700
Data Index: 1302776 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.5865. Min Act: -0.1700
Data Index: 7633076 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.5865. Min Act: -0.1700
Data Index: 8630309 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.5778. Min Act: -0.1700
Data Index: 6126432 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.5691. Min Act: -0.1700
Data Index: 1211376 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.5778. Min Act: -0.1700
Data Index: 4205441 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6737. Min Range: -1.6737
Max Act: 1.5778. Min Act: -0.1700
Data Index: 4161522 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19