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

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

Neuron 3728 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.6432. Min Act: -0.0000

Data Index: 539623 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.4759. Min Act: -0.0000

Data Index: 239510 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.6166. Min Act: -0.0001

Data Index: 1036508 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.5308. Min Act: -0.0000

Data Index: 1232740 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.3667. Min Act: -0.0001

Data Index: 501745 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.3301. Min Act: -0.0001

Data Index: 1192792 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.3509. Min Act: -0.0000

Data Index: 919207 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.3578. Min Act: -0.0000

Data Index: 504068 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.3506. Min Act: -0.0000

Data Index: 1203385 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.1673. Min Act: -0.0001

Data Index: 1626918 (Python Code)

Max Activating Token Index: 787

Text #10

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.2179. Min Act: -0.0000

Data Index: 414107 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.1301. Min Act: -0.0001

Data Index: 1429066 (Python Code)

Max Activating Token Index: 468

Text #12

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.2580. Min Act: -0.0001

Data Index: 463991 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.0884. Min Act: -0.0000

Data Index: 1184573 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.1129. Min Act: -0.0000

Data Index: 1404724 (Python Code)

Max Activating Token Index: 659

Text #15

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.1032. Min Act: -0.0000

Data Index: 750264 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.1459. Min Act: -0.0000

Data Index: 546692 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.1372. Min Act: -0.0000

Data Index: 422159 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.1030. Min Act: -0.0001

Data Index: 251531 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 1.6432. Min Range: -1.6432

Max Act: 1.1034. Min Act: -0.0000

Data Index: 1104815 (C4 (Web Text))

Max Activating Token Index: 785