Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1498 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.7555. Min Act: -0.1700
Data Index: 6370197 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.7382. Min Act: -0.1700
Data Index: 3750969 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.7296. Min Act: -0.1698
Data Index: 5115025 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.7209. Min Act: -0.1700
Data Index: 7489858 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.7036. Min Act: -0.1700
Data Index: 2574111 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.6949. Min Act: -0.1700
Data Index: 32190 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.6949. Min Act: -0.1700
Data Index: 4134672 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.6862. Min Act: -0.1700
Data Index: 8355456 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.6949. Min Act: -0.1700
Data Index: 6201337 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.6862. Min Act: -0.1700
Data Index: 2373594 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.6775. Min Act: -0.1700
Data Index: 3560355 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.6775. Min Act: -0.1700
Data Index: 7380318 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.6862. Min Act: -0.1699
Data Index: 3610581 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.6775. Min Act: -0.1700
Data Index: 1950129 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.6688. Min Act: -0.1697
Data Index: 4166508 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.6775. Min Act: -0.1700
Data Index: 1057649 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.6775. Min Act: -0.1699
Data Index: 6124285 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.6688. Min Act: -0.1700
Data Index: 2899688 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.6602. Min Act: -0.1700
Data Index: 7101645 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7555. Min Range: -1.7555
Max Act: 1.6515. Min Act: -0.1700
Data Index: 6124139 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19