Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4300 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.8907. Min Act: -0.0000

Data Index: 1827540 (The Pile)

Max Activating Token Index: 129

Text #1

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.7135. Min Act: -0.0000

Data Index: 620218 (The Pile)

Max Activating Token Index: 76

Text #2

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.3361. Min Act: -0.0000

Data Index: 1681289 (The Pile)

Max Activating Token Index: 461

Text #3

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.1919. Min Act: -0.0000

Data Index: 84593 (The Pile)

Max Activating Token Index: 101

Text #4

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.0962. Min Act: -0.0000

Data Index: 825131 (The Pile)

Max Activating Token Index: 379

Text #5

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.2040. Min Act: -0.0000

Data Index: 1777590 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.0559. Min Act: -0.0000

Data Index: 636058 (The Pile)

Max Activating Token Index: 606

Text #7

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.0428. Min Act: -0.0000

Data Index: 1305095 (The Pile)

Max Activating Token Index: 393

Text #8

Max Range: 3.8907. Min Range: -3.8907

Max Act: 2.9283. Min Act: -0.0000

Data Index: 1323525 (The Pile)

Max Activating Token Index: 796

Text #9

Max Range: 3.8907. Min Range: -3.8907

Max Act: 2.8925. Min Act: -0.0000

Data Index: 1422959 (The Pile)

Max Activating Token Index: 959

Text #10

Max Range: 3.8907. Min Range: -3.8907

Max Act: 2.9425. Min Act: -0.0000

Data Index: 630284 (The Pile)

Max Activating Token Index: 704

Text #11

Max Range: 3.8907. Min Range: -3.8907

Max Act: 2.7398. Min Act: -0.0000

Data Index: 1131767 (The Pile)

Max Activating Token Index: 821

Text #12

Max Range: 3.8907. Min Range: -3.8907

Max Act: 2.6143. Min Act: -0.0000

Data Index: 1701934 (The Pile)

Max Activating Token Index: 71

Text #13

Max Range: 3.8907. Min Range: -3.8907

Max Act: 2.7527. Min Act: -0.0000

Data Index: 1606716 (The Pile)

Max Activating Token Index: 1010

Text #14

Max Range: 3.8907. Min Range: -3.8907

Max Act: 2.6067. Min Act: -0.0000

Data Index: 1843735 (The Pile)

Max Activating Token Index: 862

Text #15

Max Range: 3.8907. Min Range: -3.8907

Max Act: 2.6920. Min Act: -0.0000

Data Index: 799585 (The Pile)

Max Activating Token Index: 704

Text #16

Max Range: 3.8907. Min Range: -3.8907

Max Act: 2.6883. Min Act: -0.0000

Data Index: 1723923 (The Pile)

Max Activating Token Index: 1006

Text #17

Max Range: 3.8907. Min Range: -3.8907

Max Act: 2.7988. Min Act: -0.0000

Data Index: 1553270 (The Pile)

Max Activating Token Index: 404

Text #18

Max Range: 3.8907. Min Range: -3.8907

Max Act: 2.4038. Min Act: -0.0000

Data Index: 432982 (The Pile)

Max Activating Token Index: 963

Text #19

Max Range: 3.8907. Min Range: -3.8907

Max Act: 2.6203. Min Act: -0.0000

Data Index: 558909 (The Pile)

Max Activating Token Index: 260