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

Dataset: The Pile

Neuron 4968 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.5756. Min Act: -0.0000

Data Index: 1333625 (The Pile)

Max Activating Token Index: 234

Text #1

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.5356. Min Act: -0.0000

Data Index: 763597 (The Pile)

Max Activating Token Index: 190

Text #2

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.5005. Min Act: -0.0000

Data Index: 1615563 (The Pile)

Max Activating Token Index: 237

Text #3

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.2285. Min Act: -0.0000

Data Index: 1497936 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.4469. Min Act: -0.0000

Data Index: 78885 (The Pile)

Max Activating Token Index: 771

Text #5

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.3467. Min Act: -0.0000

Data Index: 441459 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.2713. Min Act: -0.0000

Data Index: 1096954 (The Pile)

Max Activating Token Index: 540

Text #7

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.3361. Min Act: -0.0000

Data Index: 443664 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.1749. Min Act: -0.0000

Data Index: 1957507 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.2618. Min Act: -0.0000

Data Index: 1416312 (The Pile)

Max Activating Token Index: 353

Text #10

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.3188. Min Act: -0.0000

Data Index: 55670 (The Pile)

Max Activating Token Index: 748

Text #11

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.1022. Min Act: -0.0000

Data Index: 1789141 (The Pile)

Max Activating Token Index: 976

Text #12

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.3196. Min Act: -0.0000

Data Index: 679835 (The Pile)

Max Activating Token Index: 28

Text #13

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.2323. Min Act: -0.0000

Data Index: 277162 (The Pile)

Max Activating Token Index: 639

Text #14

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.2114. Min Act: -0.0000

Data Index: 242930 (The Pile)

Max Activating Token Index: 217

Text #15

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.1326. Min Act: -0.0000

Data Index: 1621855 (The Pile)

Max Activating Token Index: 245

Text #16

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.1864. Min Act: -0.0000

Data Index: 930213 (The Pile)

Max Activating Token Index: 587

Text #17

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.1879. Min Act: -0.0000

Data Index: 452520 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.1822. Min Act: -0.0000

Data Index: 1602380 (The Pile)

Max Activating Token Index: 680

Text #19

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.1880. Min Act: -0.0000

Data Index: 1379233 (The Pile)

Max Activating Token Index: 56