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

Dataset: The Pile

Neuron 1729 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: 0.3229. Min Range: -0.3229

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1941030 (The Pile)

Max Activating Token Index: 304

Text #1

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2455. Min Act: -0.0000

Data Index: 741842 (The Pile)

Max Activating Token Index: 929

Text #2

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2268. Min Act: -0.0000

Data Index: 1915592 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1010095 (The Pile)

Max Activating Token Index: 326

Text #4

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2296. Min Act: -0.0000

Data Index: 1750298 (The Pile)

Max Activating Token Index: 245

Text #5

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2187. Min Act: -0.0000

Data Index: 66153 (The Pile)

Max Activating Token Index: 490

Text #6

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2405. Min Act: -0.0000

Data Index: 373210 (The Pile)

Max Activating Token Index: 256

Text #7

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.1688. Min Act: -0.0000

Data Index: 716578 (The Pile)

Max Activating Token Index: 186

Text #8

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2049. Min Act: -0.0000

Data Index: 289050 (The Pile)

Max Activating Token Index: 33

Text #9

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2018. Min Act: -0.0000

Data Index: 891351 (The Pile)

Max Activating Token Index: 646

Text #10

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.1936. Min Act: -0.0000

Data Index: 1297295 (The Pile)

Max Activating Token Index: 993

Text #11

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2041. Min Act: -0.0000

Data Index: 1822589 (The Pile)

Max Activating Token Index: 594

Text #12

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2144. Min Act: -0.0000

Data Index: 602377 (The Pile)

Max Activating Token Index: 708

Text #13

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.1953. Min Act: -0.0000

Data Index: 563376 (The Pile)

Max Activating Token Index: 450

Text #14

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1379205 (The Pile)

Max Activating Token Index: 407

Text #15

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.1871. Min Act: -0.0000

Data Index: 1581912 (The Pile)

Max Activating Token Index: 13

Text #16

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.1721. Min Act: -0.0000

Data Index: 330772 (The Pile)

Max Activating Token Index: 598

Text #17

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.1870. Min Act: -0.0000

Data Index: 1412812 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.1699. Min Act: -0.0000

Data Index: 638903 (The Pile)

Max Activating Token Index: 404

Text #19

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.1855. Min Act: -0.0000

Data Index: 272889 (The Pile)

Max Activating Token Index: 567