Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.2986. Min Act: -0.1700
Data Index: 6514676 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.2673. Min Act: -0.1700
Data Index: 8476662 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.2048. Min Act: -0.1700
Data Index: 5037257 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.1736. Min Act: -0.1700
Data Index: 4493626 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.2048. Min Act: -0.1700
Data Index: 5830878 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.1736. Min Act: -0.1700
Data Index: 1881303 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.1423. Min Act: -0.1700
Data Index: 8416993 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.1423. Min Act: -0.1700
Data Index: 7772518 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.1423. Min Act: -0.1700
Data Index: 7779859 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.1111. Min Act: -0.1700
Data Index: 1939085 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.0798. Min Act: -0.1700
Data Index: 1537314 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.0798. Min Act: -0.1700
Data Index: 4239035 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.0486. Min Act: -0.1700
Data Index: 3051550 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.0798. Min Act: -0.1700
Data Index: 1042865 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.0798. Min Act: -0.1700
Data Index: 5333308 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.0486. Min Act: -0.1700
Data Index: 5180024 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.0486. Min Act: -0.1700
Data Index: 8134923 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.0486. Min Act: -0.1700
Data Index: 7308344 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2986. Min Range: -4.2986
Max Act: 4.0486. Min Act: -0.1700
Data Index: 7215179 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2986. Min Range: -4.2986
Max Act: 3.9860. Min Act: -0.1700
Data Index: 8349094 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19