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

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

Neuron 1459 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.6432. Min Act: -0.0001

Data Index: 325483 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.6365. Min Act: -0.0002

Data Index: 323997 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5699. Min Act: -0.0002

Data Index: 254844 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5699. Min Act: -0.0002

Data Index: 687420 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5844. Min Act: -0.0002

Data Index: 1292042 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5246. Min Act: -0.0002

Data Index: 571056 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5741. Min Act: -0.0001

Data Index: 194938 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5533. Min Act: -0.0002

Data Index: 687250 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5478. Min Act: -0.0001

Data Index: 78175 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5276. Min Act: -0.0001

Data Index: 854521 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5245. Min Act: -0.0001

Data Index: 342337 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5198. Min Act: -0.0001

Data Index: 692689 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5134. Min Act: -0.0001

Data Index: 552008 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5343. Min Act: -0.0002

Data Index: 1230612 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5628. Min Act: -0.0001

Data Index: 491517 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5294. Min Act: -0.0001

Data Index: 531698 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5216. Min Act: -0.0001

Data Index: 1212942 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5063. Min Act: -0.0001

Data Index: 80381 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5176. Min Act: -0.0001

Data Index: 21295 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5598. Min Act: -0.0001

Data Index: 458979 (C4 (Web Text))

Max Activating Token Index: 729