Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 347 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.8751. Min Act: -0.0000

Data Index: 366232 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.9177. Min Act: -0.0000

Data Index: 856391 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.9029. Min Act: -0.0000

Data Index: 966653 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.7530. Min Act: -0.0000

Data Index: 1155475 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.5496. Min Act: -0.0000

Data Index: 1058631 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.5497. Min Act: -0.0000

Data Index: 926721 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.5308. Min Act: -0.0000

Data Index: 1005714 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.3269. Min Act: -0.0000

Data Index: 398639 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.4970. Min Act: -0.0000

Data Index: 879951 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.3472. Min Act: -0.0000

Data Index: 1079740 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.4173. Min Act: -0.0000

Data Index: 776750 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.3997. Min Act: -0.0000

Data Index: 977520 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.3056. Min Act: -0.0000

Data Index: 1087780 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.4071. Min Act: -0.0000

Data Index: 614570 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.4495. Min Act: -0.0000

Data Index: 12619 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.4468. Min Act: -0.0000

Data Index: 1330595 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.3352. Min Act: -0.0000

Data Index: 60639 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1301655 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.3294. Min Act: -0.0000

Data Index: 492621 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.3112. Min Act: -0.0000

Data Index: 245286 (C4 (Web Text))

Max Activating Token Index: 604