Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1952 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.8051. Min Act: -0.1700
Data Index: 976136 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.6801. Min Act: -0.1700
Data Index: 6109133 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.5239. Min Act: -0.1700
Data Index: 1810603 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.5239. Min Act: -0.1700
Data Index: 8349714 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.5239. Min Act: -0.1700
Data Index: 5947845 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.5551. Min Act: -0.1700
Data Index: 943816 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.4926. Min Act: -0.1700
Data Index: 1216360 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.4613. Min Act: -0.1700
Data Index: 4978336 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.4926. Min Act: -0.1700
Data Index: 5985713 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.4613. Min Act: -0.1700
Data Index: 1805051 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.4301. Min Act: -0.1700
Data Index: 6159933 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.3988. Min Act: -0.1700
Data Index: 8776588 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.3988. Min Act: -0.1700
Data Index: 1921921 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.3988. Min Act: -0.1700
Data Index: 468716 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.3363. Min Act: -0.1700
Data Index: 2243910 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.3988. Min Act: -0.1700
Data Index: 6848783 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.3363. Min Act: -0.1700
Data Index: 8527903 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.3363. Min Act: -0.1700
Data Index: 8003409 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.3363. Min Act: -0.1700
Data Index: 768855 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8051. Min Range: -4.8051
Max Act: 4.3363. Min Act: -0.1700
Data Index: 6576932 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19