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

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

Neuron 699 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2734. Min Act: -0.0001

Data Index: 951468 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1322007 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2376. Min Act: -0.0000

Data Index: 943919 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2394. Min Act: -0.0000

Data Index: 468938 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2364. Min Act: -0.0000

Data Index: 24416 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2397. Min Act: -0.0001

Data Index: 315878 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2397. Min Act: -0.0000

Data Index: 280096 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2311. Min Act: -0.0001

Data Index: 213509 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2214. Min Act: -0.0000

Data Index: 299081 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2273. Min Act: -0.0001

Data Index: 425819 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2351. Min Act: -0.0000

Data Index: 892188 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2259. Min Act: -0.0000

Data Index: 909259 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2298. Min Act: -0.0000

Data Index: 1272594 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2130. Min Act: -0.0000

Data Index: 684209 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2206. Min Act: -0.0000

Data Index: 377084 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2129. Min Act: -0.0000

Data Index: 71407 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2072. Min Act: -0.0000

Data Index: 552406 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2147. Min Act: -0.0001

Data Index: 1383643 (Python Code)

Max Activating Token Index: 612

Text #18

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2146. Min Act: -0.0000

Data Index: 764279 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2133. Min Act: -0.0000

Data Index: 811777 (C4 (Web Text))

Max Activating Token Index: 52