Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3248 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2291. Min Act: -0.1700
Data Index: 4012363 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2291. Min Act: -0.1700
Data Index: 687507 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2291. Min Act: -0.1700
Data Index: 6835940 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2291. Min Act: -0.1697
Data Index: 7405335 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2291. Min Act: -0.1700
Data Index: 7774430 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2291. Min Act: -0.1700
Data Index: 4320560 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2291. Min Act: -0.1700
Data Index: 4597664 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2171. Min Act: -0.1700
Data Index: 7976949 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2171. Min Act: -0.1700
Data Index: 5533810 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2171. Min Act: -0.1700
Data Index: 5019972 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2171. Min Act: -0.1700
Data Index: 1389495 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2171. Min Act: -0.1700
Data Index: 3110658 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2171. Min Act: -0.1700
Data Index: 7304945 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2112. Min Act: -0.1700
Data Index: 1904029 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2112. Min Act: -0.1700
Data Index: 872686 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2112. Min Act: -0.1700
Data Index: 2441001 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2112. Min Act: -0.1695
Data Index: 3244332 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2053. Min Act: -0.1700
Data Index: 3836920 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2053. Min Act: -0.1700
Data Index: 5776351 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2291. Min Range: -0.2291
Max Act: 0.2053. Min Act: -0.1700
Data Index: 7129292 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19