Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2591 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.8827. Min Act: -0.1700
Data Index: 7516925 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.8399. Min Act: -0.1700
Data Index: 1457809 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.7970. Min Act: -0.1700
Data Index: 3854803 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.7970. Min Act: -0.1700
Data Index: 5082085 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.7883. Min Act: -0.1700
Data Index: 8468240 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.7883. Min Act: -0.1700
Data Index: 8047823 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.7883. Min Act: -0.1700
Data Index: 1640655 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.7883. Min Act: -0.1700
Data Index: 6683837 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.7883. Min Act: -0.1700
Data Index: 8685592 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.7883. Min Act: -0.1700
Data Index: 5353652 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.7711. Min Act: -0.1700
Data Index: 732133 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.7539. Min Act: -0.1700
Data Index: 4421789 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.7711. Min Act: -0.1700
Data Index: 8151108 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.7625. Min Act: -0.1700
Data Index: 5410863 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.7797. Min Act: -0.1700
Data Index: 6018233 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.7711. Min Act: -0.1699
Data Index: 431282 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.7625. Min Act: -0.1700
Data Index: 5071007 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.7539. Min Act: -0.1700
Data Index: 5142381 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.7625. Min Act: -0.1700
Data Index: 3128271 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8827. Min Range: -1.8827
Max Act: 1.7539. Min Act: -0.1700
Data Index: 8349706 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19