Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 182 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.9369. Min Act: -0.0000

Data Index: 569776 (The Pile)

Max Activating Token Index: 323

Text #1

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.9500. Min Act: -0.0000

Data Index: 1952659 (The Pile)

Max Activating Token Index: 892

Text #2

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.8674. Min Act: -0.0000

Data Index: 1684904 (The Pile)

Max Activating Token Index: 264

Text #3

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1749870 (The Pile)

Max Activating Token Index: 180

Text #4

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.8239. Min Act: -0.0000

Data Index: 1828942 (The Pile)

Max Activating Token Index: 712

Text #5

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.9117. Min Act: -0.0000

Data Index: 967023 (The Pile)

Max Activating Token Index: 95

Text #6

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.8302. Min Act: -0.0000

Data Index: 1496145 (The Pile)

Max Activating Token Index: 787

Text #7

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.8314. Min Act: -0.0000

Data Index: 1867974 (The Pile)

Max Activating Token Index: 700

Text #8

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1526675 (The Pile)

Max Activating Token Index: 60

Text #9

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7632. Min Act: -0.0000

Data Index: 523812 (The Pile)

Max Activating Token Index: 394

Text #10

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.8129. Min Act: -0.0000

Data Index: 17989 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1127505 (The Pile)

Max Activating Token Index: 207

Text #12

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1972767 (The Pile)

Max Activating Token Index: 960

Text #13

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.8236. Min Act: -0.0000

Data Index: 978462 (The Pile)

Max Activating Token Index: 119

Text #14

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7370. Min Act: -0.0000

Data Index: 938047 (The Pile)

Max Activating Token Index: 514

Text #15

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1540157 (The Pile)

Max Activating Token Index: 734

Text #16

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7504. Min Act: -0.0000

Data Index: 653324 (The Pile)

Max Activating Token Index: 278

Text #17

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7503. Min Act: -0.0000

Data Index: 585627 (The Pile)

Max Activating Token Index: 681

Text #18

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7135. Min Act: -0.0000

Data Index: 232831 (The Pile)

Max Activating Token Index: 889

Text #19

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.6540. Min Act: -0.0000

Data Index: 461268 (The Pile)

Max Activating Token Index: 574