Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1556 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.6733. Min Act: -0.1700
Data Index: 5398465 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.5769. Min Act: -0.1700
Data Index: 652961 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.5769. Min Act: -0.1700
Data Index: 749922 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.5285. Min Act: -0.1700
Data Index: 6689262 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.5285. Min Act: -0.1700
Data Index: 4467675 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.4636. Min Act: -0.1700
Data Index: 8417153 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.4636. Min Act: -0.1700
Data Index: 7685460 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.4636. Min Act: -0.1700
Data Index: 8417154 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.4636. Min Act: -0.1691
Data Index: 4495584 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.4311. Min Act: -0.1700
Data Index: 8066894 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.3985. Min Act: -0.1700
Data Index: 5463224 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.3658. Min Act: -0.1700
Data Index: 3273455 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.3495. Min Act: -0.1700
Data Index: 7148096 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.3495. Min Act: -0.1700
Data Index: 1494856 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.3331. Min Act: -0.1700
Data Index: 1903936 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.3331. Min Act: -0.1692
Data Index: 5979986 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.3166. Min Act: -0.1700
Data Index: 4582992 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.2837. Min Act: -0.1700
Data Index: 1889519 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.2837. Min Act: -0.1700
Data Index: 7118828 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6733. Min Range: -2.6733
Max Act: 2.2837. Min Act: -0.1700
Data Index: 1408089 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19