Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3911 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0358. Min Range: -1.0358

Max Act: 1.0358. Min Act: -0.0002

Data Index: 1351551 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.9254. Min Act: -0.0001

Data Index: 118217 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.8243. Min Act: -0.0002

Data Index: 1288413 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7476. Min Act: -0.0002

Data Index: 173752 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7587. Min Act: -0.0002

Data Index: 202433 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6815. Min Act: -0.0001

Data Index: 704042 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6363. Min Act: -0.0001

Data Index: 1206765 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7143. Min Act: -0.0001

Data Index: 400272 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6658. Min Act: -0.0002

Data Index: 1155175 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7097. Min Act: -0.0002

Data Index: 336823 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6232. Min Act: -0.0001

Data Index: 1079592 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6781. Min Act: -0.0001

Data Index: 1300013 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6547. Min Act: -0.0001

Data Index: 1311055 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6178. Min Act: -0.0002

Data Index: 1281923 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6207. Min Act: -0.0002

Data Index: 565717 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6537. Min Act: -0.0001

Data Index: 1246910 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6341. Min Act: -0.0002

Data Index: 7134 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6590. Min Act: -0.0001

Data Index: 174125 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6587. Min Act: -0.0002

Data Index: 349504 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6498. Min Act: -0.0002

Data Index: 6601 (C4 (Web Text))

Max Activating Token Index: 69