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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 80 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2364. Min Act: -0.0000

Data Index: 192178 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2241. Min Act: -0.0000

Data Index: 569182 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2146. Min Act: -0.0000

Data Index: 860648 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1079308 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2185. Min Act: -0.0000

Data Index: 606972 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1585911 (Python Code)

Max Activating Token Index: 118

Text #6

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2139. Min Act: -0.0000

Data Index: 631351 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2167. Min Act: -0.0000

Data Index: 1604802 (Python Code)

Max Activating Token Index: 248

Text #8

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1996. Min Act: -0.0000

Data Index: 939645 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2128. Min Act: -0.0000

Data Index: 196843 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2292. Min Act: -0.0000

Data Index: 693607 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2026. Min Act: -0.0000

Data Index: 321083 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1917. Min Act: -0.0000

Data Index: 1094615 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2008. Min Act: -0.0000

Data Index: 426273 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2036. Min Act: -0.0000

Data Index: 113470 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1643180 (Python Code)

Max Activating Token Index: 348

Text #16

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1898. Min Act: -0.0000

Data Index: 201742 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2027. Min Act: -0.0000

Data Index: 34412 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1308863 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2006. Min Act: -0.0000

Data Index: 524242 (C4 (Web Text))

Max Activating Token Index: 393