Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5079 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.7691. Min Act: -0.1700
Data Index: 4907883 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.5191. Min Act: -0.1700
Data Index: 8637 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.4566. Min Act: -0.1700
Data Index: 1980057 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.3941. Min Act: -0.1700
Data Index: 8403448 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.2379. Min Act: -0.1700
Data Index: 7288103 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.2691. Min Act: -0.1700
Data Index: 1103598 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.2691. Min Act: -0.1700
Data Index: 7005776 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.2379. Min Act: -0.1700
Data Index: 3294509 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.2066. Min Act: -0.1700
Data Index: 4468121 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.2379. Min Act: -0.1700
Data Index: 2262144 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.2066. Min Act: -0.1700
Data Index: 3393065 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.2066. Min Act: -0.1700
Data Index: 3011282 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.1754. Min Act: -0.1700
Data Index: 8102795 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.1754. Min Act: -0.1700
Data Index: 6499372 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.1441. Min Act: -0.1700
Data Index: 1439753 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.1129. Min Act: -0.1700
Data Index: 1042729 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.1129. Min Act: -0.1700
Data Index: 7296128 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.1129. Min Act: -0.1700
Data Index: 3498984 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.0816. Min Act: -0.1700
Data Index: 6223006 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7691. Min Range: -5.7691
Max Act: 5.0816. Min Act: -0.1700
Data Index: 899167 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19