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

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

Neuron 4142 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: 0.6556. Min Range: -0.6556

Max Act: 0.6547. Min Act: -0.0000

Data Index: 810540 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.6204. Min Act: -0.0000

Data Index: 102387 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.6249. Min Act: -0.0000

Data Index: 394292 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5825. Min Act: -0.0000

Data Index: 973032 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5909. Min Act: -0.0000

Data Index: 1003893 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.6556. Min Act: -0.0000

Data Index: 496440 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5453. Min Act: -0.0000

Data Index: 388257 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1265323 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5285. Min Act: -0.0000

Data Index: 949362 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5188. Min Act: -0.0000

Data Index: 367514 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5199. Min Act: -0.0000

Data Index: 951488 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1316741 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5302. Min Act: -0.0000

Data Index: 410270 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4934. Min Act: -0.0000

Data Index: 135766 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5075. Min Act: -0.0000

Data Index: 223732 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4943. Min Act: -0.0000

Data Index: 163473 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1179633 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4830. Min Act: -0.0000

Data Index: 390741 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4906. Min Act: -0.0000

Data Index: 442746 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4485. Min Act: -0.0000

Data Index: 498149 (C4 (Web Text))

Max Activating Token Index: 99