Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4256 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.8311. Min Act: -0.1700
Data Index: 3941247 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.7450. Min Act: -0.1700
Data Index: 1752303 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.7104. Min Act: -0.1700
Data Index: 7763697 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.7104. Min Act: -0.1700
Data Index: 4046859 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.7104. Min Act: -0.1700
Data Index: 7227417 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.6757. Min Act: -0.1700
Data Index: 5122144 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.6930. Min Act: -0.1700
Data Index: 8450235 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.6757. Min Act: -0.1700
Data Index: 5339827 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.6757. Min Act: -0.1700
Data Index: 2238842 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.6930. Min Act: -0.1700
Data Index: 3706821 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.6583. Min Act: -0.1700
Data Index: 3390661 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.6583. Min Act: -0.1700
Data Index: 4330391 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.6757. Min Act: -0.1700
Data Index: 4099039 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.6234. Min Act: -0.1700
Data Index: 5245531 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.6409. Min Act: -0.1700
Data Index: 6943689 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.6409. Min Act: -0.1700
Data Index: 3020317 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.6234. Min Act: -0.1700
Data Index: 8161218 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.6234. Min Act: -0.1700
Data Index: 3452683 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.6060. Min Act: -0.1700
Data Index: 5876991 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8311. Min Range: -1.8311
Max Act: 1.6234. Min Act: -0.1700
Data Index: 307610 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19