Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2062 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4137. Min Range: -8.4137
Max Act: 8.4137. Min Act: -0.1700
Data Index: 7509806 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4137. Min Range: -8.4137
Max Act: 8.0699. Min Act: -0.1700
Data Index: 3417354 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4137. Min Range: -8.4137
Max Act: 7.8824. Min Act: -0.1700
Data Index: 7131519 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4137. Min Range: -8.4137
Max Act: 7.8824. Min Act: -0.1700
Data Index: 3774044 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4137. Min Range: -8.4137
Max Act: 7.8824. Min Act: -0.1700
Data Index: 5355585 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4137. Min Range: -8.4137
Max Act: 7.7262. Min Act: -0.1700
Data Index: 4931885 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4137. Min Range: -8.4137
Max Act: 7.6949. Min Act: -0.1700
Data Index: 2573647 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4137. Min Range: -8.4137
Max Act: 7.6637. Min Act: -0.1700
Data Index: 8087061 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4137. Min Range: -8.4137
Max Act: 7.5699. Min Act: -0.1700
Data Index: 3957798 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4137. Min Range: -8.4137
Max Act: 7.6637. Min Act: -0.1700
Data Index: 8234743 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4137. Min Range: -8.4137
Max Act: 7.5387. Min Act: -0.1700
Data Index: 701392 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4137. Min Range: -8.4137
Max Act: 7.4449. Min Act: -0.1700
Data Index: 4748083 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4137. Min Range: -8.4137
Max Act: 7.5074. Min Act: -0.1700
Data Index: 3748323 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4137. Min Range: -8.4137
Max Act: 7.5387. Min Act: -0.1700
Data Index: 7652575 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4137. Min Range: -8.4137
Max Act: 7.4762. Min Act: -0.1700
Data Index: 4741984 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4137. Min Range: -8.4137
Max Act: 7.4449. Min Act: -0.1700
Data Index: 494397 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4137. Min Range: -8.4137
Max Act: 7.3824. Min Act: -0.1700
Data Index: 1975449 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4137. Min Range: -8.4137
Max Act: 7.4137. Min Act: -0.1700
Data Index: 5951349 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4137. Min Range: -8.4137
Max Act: 7.4137. Min Act: -0.1700
Data Index: 3783602 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4137. Min Range: -8.4137
Max Act: 7.3824. Min Act: -0.1700
Data Index: 2371334 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19