Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 289 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.0696. Min Range: -9.0696
Max Act: 9.0696. Min Act: -0.1700
Data Index: 2756751 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0696. Min Range: -9.0696
Max Act: 8.5071. Min Act: -0.1700
Data Index: 4452327 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0696. Min Range: -9.0696
Max Act: 8.3196. Min Act: -0.1700
Data Index: 9494 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0696. Min Range: -9.0696
Max Act: 8.2571. Min Act: -0.1699
Data Index: 404071 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0696. Min Range: -9.0696
Max Act: 8.1946. Min Act: -0.1700
Data Index: 493635 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0696. Min Range: -9.0696
Max Act: 7.9446. Min Act: -0.1700
Data Index: 2139330 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0696. Min Range: -9.0696
Max Act: 7.8821. Min Act: -0.1700
Data Index: 4214085 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0696. Min Range: -9.0696
Max Act: 7.8196. Min Act: -0.1699
Data Index: 4214086 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0696. Min Range: -9.0696
Max Act: 7.8196. Min Act: -0.1700
Data Index: 6585609 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0696. Min Range: -9.0696
Max Act: 7.7571. Min Act: -0.1700
Data Index: 7404600 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0696. Min Range: -9.0696
Max Act: 7.6946. Min Act: -0.1699
Data Index: 5433464 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0696. Min Range: -9.0696
Max Act: 7.6946. Min Act: -0.1700
Data Index: 3619287 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0696. Min Range: -9.0696
Max Act: 7.7571. Min Act: -0.1700
Data Index: 1044910 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0696. Min Range: -9.0696
Max Act: 7.6946. Min Act: -0.1700
Data Index: 8537386 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0696. Min Range: -9.0696
Max Act: 7.6321. Min Act: -0.1700
Data Index: 8528487 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0696. Min Range: -9.0696
Max Act: 7.6321. Min Act: -0.1700
Data Index: 3986507 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0696. Min Range: -9.0696
Max Act: 7.6321. Min Act: -0.1700
Data Index: 1924412 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0696. Min Range: -9.0696
Max Act: 7.5696. Min Act: -0.1700
Data Index: 4936478 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0696. Min Range: -9.0696
Max Act: 7.5696. Min Act: -0.1700
Data Index: 5841914 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0696. Min Range: -9.0696
Max Act: 7.5071. Min Act: -0.1700
Data Index: 4357808 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19