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

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

Neuron 1762 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1397. Min Range: -1.1397

Max Act: 1.1397. Min Act: -0.0000

Data Index: 1075039 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.7929. Min Act: -0.0000

Data Index: 1246327 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8464. Min Act: 0.0000

Data Index: 637250 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8338. Min Act: -0.0000

Data Index: 503621 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.7806. Min Act: -0.0000

Data Index: 908733 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.7586. Min Act: -0.0000

Data Index: 1536 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.7865. Min Act: -0.0000

Data Index: 304048 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1015725 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.7130. Min Act: -0.0000

Data Index: 161309 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.7164. Min Act: -0.0000

Data Index: 721717 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.7303. Min Act: -0.0000

Data Index: 151957 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.6953. Min Act: -0.0000

Data Index: 48179 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.6829. Min Act: 0.0001

Data Index: 603076 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.7191. Min Act: 0.0000

Data Index: 1324281 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.7115. Min Act: -0.0000

Data Index: 107244 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.6826. Min Act: -0.0000

Data Index: 1130078 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.6574. Min Act: -0.0000

Data Index: 180366 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.6912. Min Act: -0.0000

Data Index: 68302 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.6805. Min Act: -0.0000

Data Index: 637596 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.6490. Min Act: -0.0000

Data Index: 317026 (C4 (Web Text))

Max Activating Token Index: 512