Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 845 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6915. Min Range: -7.6915
Max Act: 7.6915. Min Act: -0.1700
Data Index: 8171928 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6915. Min Range: -7.6915
Max Act: 7.2852. Min Act: -0.1700
Data Index: 6651525 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6915. Min Range: -7.6915
Max Act: 7.1602. Min Act: -0.1700
Data Index: 5531936 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6915. Min Range: -7.6915
Max Act: 7.1290. Min Act: -0.1700
Data Index: 5352378 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6915. Min Range: -7.6915
Max Act: 7.0977. Min Act: -0.1700
Data Index: 5111588 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6915. Min Range: -7.6915
Max Act: 7.0665. Min Act: -0.1700
Data Index: 3512243 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6915. Min Range: -7.6915
Max Act: 7.0352. Min Act: -0.1700
Data Index: 2583377 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6915. Min Range: -7.6915
Max Act: 7.0040. Min Act: -0.1700
Data Index: 1183418 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9727. Min Act: -0.1699
Data Index: 5739313 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9727. Min Act: -0.1700
Data Index: 6041913 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9415. Min Act: -0.1700
Data Index: 4606009 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9727. Min Act: -0.1700
Data Index: 5400465 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9727. Min Act: -0.1700
Data Index: 2890662 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9727. Min Act: -0.1700
Data Index: 1026106 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9102. Min Act: -0.1700
Data Index: 8279234 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9415. Min Act: -0.1700
Data Index: 490665 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9415. Min Act: -0.1700
Data Index: 5646394 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9415. Min Act: -0.1700
Data Index: 58051 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9102. Min Act: -0.1700
Data Index: 2381733 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9102. Min Act: -0.1700
Data Index: 2257102 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19