Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3452 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0848. Min Range: -3.0848
Max Act: 3.0848. Min Act: -0.1700
Data Index: 1624848 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.9109. Min Act: -0.1700
Data Index: 6457566 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.9109. Min Act: -0.1700
Data Index: 2376000 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.7997. Min Act: -0.1700
Data Index: 1624846 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.8156. Min Act: -0.1700
Data Index: 1459790 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.7838. Min Act: -0.1700
Data Index: 4936865 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.7838. Min Act: -0.1700
Data Index: 2390582 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.7359. Min Act: -0.1700
Data Index: 5494163 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.7199. Min Act: -0.1700
Data Index: 2171143 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.7359. Min Act: -0.1700
Data Index: 702181 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.7199. Min Act: -0.1700
Data Index: 7573057 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.7359. Min Act: -0.1700
Data Index: 4324511 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.7040. Min Act: -0.1700
Data Index: 1019116 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.6879. Min Act: -0.1700
Data Index: 3833633 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.6879. Min Act: -0.1700
Data Index: 3948116 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.6879. Min Act: -0.1700
Data Index: 3691802 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.7040. Min Act: -0.1700
Data Index: 8209906 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.7040. Min Act: -0.1700
Data Index: 1624842 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.6879. Min Act: -0.1700
Data Index: 3629868 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0848. Min Range: -3.0848
Max Act: 2.6879. Min Act: -0.1700
Data Index: 4936857 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19