Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.6435. Min Act: -0.1700
Data Index: 8138334 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.5183. Min Act: -0.1700
Data Index: 8120497 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.4870. Min Act: -0.1700
Data Index: 2585646 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.3929. Min Act: -0.1700
Data Index: 4123631 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.3616. Min Act: -0.1700
Data Index: 1569211 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.3616. Min Act: -0.1700
Data Index: 486933 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.3459. Min Act: -0.1700
Data Index: 8641076 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.3616. Min Act: -0.1700
Data Index: 156336 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.3459. Min Act: -0.1700
Data Index: 5984355 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.3459. Min Act: -0.1700
Data Index: 8350350 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.3302. Min Act: -0.1700
Data Index: 2009921 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.3459. Min Act: -0.1700
Data Index: 8045171 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.3302. Min Act: -0.1700
Data Index: 8389616 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.3302. Min Act: -0.1700
Data Index: 6092493 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.3302. Min Act: -0.1700
Data Index: 6659552 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.3302. Min Act: -0.1700
Data Index: 6701773 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.3302. Min Act: -0.1700
Data Index: 1881629 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.3145. Min Act: -0.1700
Data Index: 2170738 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.3145. Min Act: -0.1700
Data Index: 6150528 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6435. Min Range: -3.6435
Max Act: 3.3145. Min Act: -0.1700
Data Index: 853967 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19