Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2100 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.7027. Min Act: -0.1700
Data Index: 6006884 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.6402. Min Act: -0.1700
Data Index: 4645359 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.5777. Min Act: -0.1700
Data Index: 3649524 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.5152. Min Act: -0.1700
Data Index: 7843653 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.4527. Min Act: -0.1700
Data Index: 8776097 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.4527. Min Act: -0.1700
Data Index: 7339278 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.2652. Min Act: -0.1700
Data Index: 1256167 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.3277. Min Act: -0.1700
Data Index: 7372100 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.3277. Min Act: -0.1700
Data Index: 1300316 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.2652. Min Act: -0.1700
Data Index: 1119852 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.2027. Min Act: -0.1700
Data Index: 5492422 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.2027. Min Act: -0.1700
Data Index: 3614574 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.2027. Min Act: -0.1700
Data Index: 3426911 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.2027. Min Act: -0.1700
Data Index: 5110478 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.1402. Min Act: -0.1700
Data Index: 1883629 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.1402. Min Act: -0.1700
Data Index: 4203072 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.0777. Min Act: -0.1700
Data Index: 6283211 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.0777. Min Act: -0.1700
Data Index: 834395 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.0777. Min Act: -0.1700
Data Index: 5699021 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.7027. Min Range: -11.7027
Max Act: 11.0777. Min Act: -0.1700
Data Index: 6003461 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19