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

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

Neuron 4681 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: 1.2788. Min Range: -1.2788

Max Act: 1.2788. Min Act: -0.0000

Data Index: 1308464 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9774. Min Act: -0.0000

Data Index: 505463 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.8640. Min Act: -0.0000

Data Index: 1280605 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.9177. Min Act: -0.0000

Data Index: 47006 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.8461. Min Act: -0.0000

Data Index: 928359 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.8732. Min Act: -0.0000

Data Index: 205232 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.8189. Min Act: -0.0000

Data Index: 754469 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.7969. Min Act: -0.0000

Data Index: 213204 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.7572. Min Act: -0.0000

Data Index: 264959 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.8181. Min Act: -0.0000

Data Index: 335488 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.7814. Min Act: -0.0000

Data Index: 947571 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.7622. Min Act: -0.0000

Data Index: 916844 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.8037. Min Act: -0.0000

Data Index: 207468 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.7185. Min Act: -0.0000

Data Index: 370382 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.7650. Min Act: -0.0000

Data Index: 67949 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.7335. Min Act: -0.0000

Data Index: 632923 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.7741. Min Act: -0.0000

Data Index: 548224 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1344667 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.7254. Min Act: -0.0000

Data Index: 635432 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 1.2788. Min Range: -1.2788

Max Act: 0.7071. Min Act: -0.0000

Data Index: 734573 (C4 (Web Text))

Max Activating Token Index: 377