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

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

Neuron 400 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: 0.6740. Min Range: -0.6740

Max Act: 0.6740. Min Act: -0.0000

Data Index: 787101 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.5800. Min Act: -0.0000

Data Index: 877052 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4902. Min Act: -0.0000

Data Index: 1180864 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1345436 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1062412 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1112490 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1342857 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4775. Min Act: -0.0000

Data Index: 173414 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1020790 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1297394 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4361. Min Act: -0.0000

Data Index: 1038794 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4203. Min Act: -0.0000

Data Index: 343651 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4305. Min Act: -0.0000

Data Index: 71628 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4459. Min Act: -0.0000

Data Index: 728131 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4396. Min Act: -0.0000

Data Index: 369765 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1298243 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4292. Min Act: -0.0000

Data Index: 755436 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4191. Min Act: -0.0000

Data Index: 116617 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1209332 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.3974. Min Act: -0.0000

Data Index: 521549 (C4 (Web Text))

Max Activating Token Index: 338