Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1083 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 12.1986. Min Range: -12.1986
Max Act: 12.1986. Min Act: -0.1700
Data Index: 2006388 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1986. Min Range: -12.1986
Max Act: 12.0111. Min Act: -0.1700
Data Index: 8111158 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1986. Min Range: -12.1986
Max Act: 11.6986. Min Act: -0.1700
Data Index: 221281 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1986. Min Range: -12.1986
Max Act: 11.6361. Min Act: -0.1700
Data Index: 7836401 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1986. Min Range: -12.1986
Max Act: 11.6986. Min Act: -0.1700
Data Index: 4894672 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1986. Min Range: -12.1986
Max Act: 11.6986. Min Act: -0.1700
Data Index: 7565390 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1986. Min Range: -12.1986
Max Act: 11.5736. Min Act: -0.1700
Data Index: 6481918 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1986. Min Range: -12.1986
Max Act: 11.5736. Min Act: -0.1700
Data Index: 8321383 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1986. Min Range: -12.1986
Max Act: 11.5736. Min Act: -0.1700
Data Index: 2170363 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1986. Min Range: -12.1986
Max Act: 11.5736. Min Act: -0.1700
Data Index: 4872506 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1986. Min Range: -12.1986
Max Act: 11.5111. Min Act: -0.1700
Data Index: 3412043 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1986. Min Range: -12.1986
Max Act: 11.5111. Min Act: -0.1700
Data Index: 687145 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1986. Min Range: -12.1986
Max Act: 11.5111. Min Act: -0.1700
Data Index: 6444006 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1986. Min Range: -12.1986
Max Act: 11.5111. Min Act: -0.1700
Data Index: 8656326 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1986. Min Range: -12.1986
Max Act: 11.4486. Min Act: -0.1700
Data Index: 1848936 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1986. Min Range: -12.1986
Max Act: 11.4486. Min Act: -0.1700
Data Index: 4621930 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1986. Min Range: -12.1986
Max Act: 11.4486. Min Act: -0.1700
Data Index: 3738943 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1986. Min Range: -12.1986
Max Act: 11.4486. Min Act: -0.1700
Data Index: 2473191 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1986. Min Range: -12.1986
Max Act: 11.4486. Min Act: -0.1700
Data Index: 3929913 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1986. Min Range: -12.1986
Max Act: 11.3861. Min Act: -0.1700
Data Index: 7649154 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19