Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0405. Min Range: -6.0405
Max Act: 6.0405. Min Act: -0.1700
Data Index: 3586903 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0405. Min Range: -6.0405
Max Act: 6.0092. Min Act: -0.1700
Data Index: 5632552 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0405. Min Range: -6.0405
Max Act: 6.0405. Min Act: -0.1700
Data Index: 6521189 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0405. Min Range: -6.0405
Max Act: 6.0405. Min Act: -0.1700
Data Index: 2286207 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0405. Min Range: -6.0405
Max Act: 6.0405. Min Act: -0.1700
Data Index: 6562906 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0405. Min Range: -6.0405
Max Act: 6.0092. Min Act: -0.1700
Data Index: 8521515 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0405. Min Range: -6.0405
Max Act: 6.0092. Min Act: -0.1700
Data Index: 1072062 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0405. Min Range: -6.0405
Max Act: 5.9780. Min Act: -0.1700
Data Index: 738373 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0405. Min Range: -6.0405
Max Act: 6.0092. Min Act: -0.1700
Data Index: 1334444 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0405. Min Range: -6.0405
Max Act: 6.0092. Min Act: -0.1700
Data Index: 4476519 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0405. Min Range: -6.0405
Max Act: 5.9780. Min Act: -0.1700
Data Index: 3285167 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0405. Min Range: -6.0405
Max Act: 5.9780. Min Act: -0.1700
Data Index: 375165 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0405. Min Range: -6.0405
Max Act: 5.9780. Min Act: -0.1700
Data Index: 605166 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0405. Min Range: -6.0405
Max Act: 5.9780. Min Act: -0.1700
Data Index: 8081215 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0405. Min Range: -6.0405
Max Act: 5.9780. Min Act: -0.1700
Data Index: 3814229 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0405. Min Range: -6.0405
Max Act: 5.9780. Min Act: -0.1700
Data Index: 8807152 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0405. Min Range: -6.0405
Max Act: 5.9467. Min Act: -0.1700
Data Index: 1777293 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0405. Min Range: -6.0405
Max Act: 5.9467. Min Act: -0.1700
Data Index: 6911980 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0405. Min Range: -6.0405
Max Act: 5.9467. Min Act: -0.1699
Data Index: 6105664 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0405. Min Range: -6.0405
Max Act: 5.9467. Min Act: -0.1700
Data Index: 8310973 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19