Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 425 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1748. Min Range: -5.1748
Max Act: 5.1123. Min Act: -0.1700
Data Index: 810366 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1748. Min Range: -5.1748
Max Act: 5.1123. Min Act: -0.1700
Data Index: 4920077 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1748. Min Range: -5.1748
Max Act: 5.1748. Min Act: -0.1700
Data Index: 8569740 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1748. Min Range: -5.1748
Max Act: 5.0498. Min Act: -0.1700
Data Index: 5197480 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1748. Min Range: -5.1748
Max Act: 5.0185. Min Act: -0.1700
Data Index: 3254795 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1748. Min Range: -5.1748
Max Act: 5.0185. Min Act: -0.1700
Data Index: 3013742 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1748. Min Range: -5.1748
Max Act: 5.0185. Min Act: -0.1700
Data Index: 7772277 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1748. Min Range: -5.1748
Max Act: 4.9873. Min Act: -0.1700
Data Index: 3206484 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1748. Min Range: -5.1748
Max Act: 4.9873. Min Act: -0.1700
Data Index: 913015 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1748. Min Range: -5.1748
Max Act: 4.9248. Min Act: -0.1700
Data Index: 4824575 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1748. Min Range: -5.1748
Max Act: 4.9248. Min Act: -0.1700
Data Index: 4418746 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1748. Min Range: -5.1748
Max Act: 4.9248. Min Act: -0.1700
Data Index: 7061639 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1748. Min Range: -5.1748
Max Act: 4.9248. Min Act: -0.1700
Data Index: 8014311 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1748. Min Range: -5.1748
Max Act: 4.9248. Min Act: -0.1700
Data Index: 122522 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1748. Min Range: -5.1748
Max Act: 4.8935. Min Act: -0.1700
Data Index: 309571 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1748. Min Range: -5.1748
Max Act: 4.8935. Min Act: -0.1700
Data Index: 8354687 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1748. Min Range: -5.1748
Max Act: 4.8935. Min Act: -0.1700
Data Index: 5406151 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1748. Min Range: -5.1748
Max Act: 4.8623. Min Act: -0.1700
Data Index: 7259524 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1748. Min Range: -5.1748
Max Act: 4.8623. Min Act: -0.1700
Data Index: 6696209 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1748. Min Range: -5.1748
Max Act: 4.7998. Min Act: -0.1700
Data Index: 5605872 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19