Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 7 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.2415. Min Act: -0.1700
Data Index: 1009021 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.2415. Min Act: -0.1700
Data Index: 794139 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.1790. Min Act: -0.1700
Data Index: 3281760 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.1477. Min Act: -0.1700
Data Index: 65418 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.1165. Min Act: -0.1699
Data Index: 3325976 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.1165. Min Act: -0.1700
Data Index: 4546404 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.0852. Min Act: -0.1700
Data Index: 4445826 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.0852. Min Act: -0.1700
Data Index: 5213040 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.0852. Min Act: -0.1700
Data Index: 3941516 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.0852. Min Act: -0.1700
Data Index: 1799952 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.0852. Min Act: -0.1700
Data Index: 6068145 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.0852. Min Act: -0.1700
Data Index: 6183853 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.0227. Min Act: -0.1700
Data Index: 1988007 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.0540. Min Act: -0.1699
Data Index: 1472752 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.0540. Min Act: -0.1700
Data Index: 2013746 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.0540. Min Act: -0.1700
Data Index: 2383500 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.0540. Min Act: -0.1700
Data Index: 5149586 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.0540. Min Act: -0.1700
Data Index: 5582891 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.0540. Min Act: -0.1700
Data Index: 811972 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2415. Min Range: -4.2415
Max Act: 4.0227. Min Act: -0.1700
Data Index: 3823638 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19