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

Dataset: The Pile

Neuron 2731 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6242. Min Range: -1.6242

Max Act: 1.6242. Min Act: -0.0000

Data Index: 918509 (The Pile)

Max Activating Token Index: 797

Text #1

Max Range: 1.6242. Min Range: -1.6242

Max Act: 1.3489. Min Act: -0.0000

Data Index: 142147 (The Pile)

Max Activating Token Index: 609

Text #2

Max Range: 1.6242. Min Range: -1.6242

Max Act: 1.3451. Min Act: -0.0000

Data Index: 1685982 (The Pile)

Max Activating Token Index: 71

Text #3

Max Range: 1.6242. Min Range: -1.6242

Max Act: 1.3119. Min Act: -0.0000

Data Index: 1761553 (The Pile)

Max Activating Token Index: 304

Text #4

Max Range: 1.6242. Min Range: -1.6242

Max Act: 1.3368. Min Act: -0.0000

Data Index: 1344951 (The Pile)

Max Activating Token Index: 547

Text #5

Max Range: 1.6242. Min Range: -1.6242

Max Act: 1.0095. Min Act: -0.0000

Data Index: 1495269 (The Pile)

Max Activating Token Index: 1009

Text #6

Max Range: 1.6242. Min Range: -1.6242

Max Act: 0.9831. Min Act: -0.0000

Data Index: 1557592 (The Pile)

Max Activating Token Index: 357

Text #7

Max Range: 1.6242. Min Range: -1.6242

Max Act: 1.0382. Min Act: -0.0000

Data Index: 579811 (The Pile)

Max Activating Token Index: 112

Text #8

Max Range: 1.6242. Min Range: -1.6242

Max Act: 0.9862. Min Act: -0.0000

Data Index: 1751055 (The Pile)

Max Activating Token Index: 1003

Text #9

Max Range: 1.6242. Min Range: -1.6242

Max Act: 0.9065. Min Act: -0.0000

Data Index: 319517 (The Pile)

Max Activating Token Index: 791

Text #10

Max Range: 1.6242. Min Range: -1.6242

Max Act: 1.0376. Min Act: -0.0000

Data Index: 1750826 (The Pile)

Max Activating Token Index: 610

Text #11

Max Range: 1.6242. Min Range: -1.6242

Max Act: 0.9694. Min Act: -0.0000

Data Index: 1394125 (The Pile)

Max Activating Token Index: 1017

Text #12

Max Range: 1.6242. Min Range: -1.6242

Max Act: 0.9133. Min Act: -0.0000

Data Index: 1253409 (The Pile)

Max Activating Token Index: 499

Text #13

Max Range: 1.6242. Min Range: -1.6242

Max Act: 0.9112. Min Act: -0.0000

Data Index: 1943132 (The Pile)

Max Activating Token Index: 167

Text #14

Max Range: 1.6242. Min Range: -1.6242

Max Act: 0.8093. Min Act: -0.0000

Data Index: 195019 (The Pile)

Max Activating Token Index: 700

Text #15

Max Range: 1.6242. Min Range: -1.6242

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1805918 (The Pile)

Max Activating Token Index: 616

Text #16

Max Range: 1.6242. Min Range: -1.6242

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1659742 (The Pile)

Max Activating Token Index: 574

Text #17

Max Range: 1.6242. Min Range: -1.6242

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1980395 (The Pile)

Max Activating Token Index: 119

Text #18

Max Range: 1.6242. Min Range: -1.6242

Max Act: 0.7429. Min Act: -0.0000

Data Index: 1879141 (The Pile)

Max Activating Token Index: 166

Text #19

Max Range: 1.6242. Min Range: -1.6242

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1334712 (The Pile)

Max Activating Token Index: 512