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

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

Neuron 1632 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1192633 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0473. Min Act: -0.0002

Data Index: 605283 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0441. Min Act: -0.0002

Data Index: 774168 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0400. Min Act: -0.0002

Data Index: 557039 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0396. Min Act: -0.0002

Data Index: 573300 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0345. Min Act: -0.0003

Data Index: 628866 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0316. Min Act: -0.0003

Data Index: 435498 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0326. Min Act: -0.0002

Data Index: 477440 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0330. Min Act: -0.0003

Data Index: 970731 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1163322 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0327. Min Act: -0.0003

Data Index: 78158 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1202538 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0323. Min Act: -0.0002

Data Index: 126417 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0329. Min Act: -0.0002

Data Index: 347444 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0320. Min Act: -0.0003

Data Index: 286907 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0313. Min Act: -0.0003

Data Index: 180539 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1149863 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0303. Min Act: -0.0002

Data Index: 589347 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0320. Min Act: -0.0003

Data Index: 802976 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0304. Min Act: -0.0002

Data Index: 973100 (C4 (Web Text))

Max Activating Token Index: 455