Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2993 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.4667. Min Act: -0.1700
Data Index: 4996801 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.3729. Min Act: -0.1700
Data Index: 5211434 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.3417. Min Act: -0.1700
Data Index: 3229994 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.3417. Min Act: -0.1700
Data Index: 5972533 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.3104. Min Act: -0.1700
Data Index: 1500188 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2792. Min Act: -0.1698
Data Index: 5037763 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2792. Min Act: -0.1700
Data Index: 5698042 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2792. Min Act: -0.1700
Data Index: 4408282 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2792. Min Act: -0.1700
Data Index: 3916697 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2479. Min Act: -0.1700
Data Index: 3690265 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2479. Min Act: -0.1700
Data Index: 3516821 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2479. Min Act: -0.1700
Data Index: 3052097 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2479. Min Act: -0.1700
Data Index: 2420840 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2479. Min Act: -0.1700
Data Index: 3137564 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2479. Min Act: -0.1700
Data Index: 5400972 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2479. Min Act: -0.1700
Data Index: 1408276 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2479. Min Act: -0.1700
Data Index: 1457809 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2479. Min Act: -0.1700
Data Index: 1020577 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2792. Min Act: -0.1700
Data Index: 3332308 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2479. Min Act: -0.1700
Data Index: 5736655 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19