Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 991 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0403. Min Act: -0.0001

Data Index: 652797 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0398. Min Act: -0.0003

Data Index: 615266 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0387. Min Act: -0.0002

Data Index: 150986 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0381. Min Act: -0.0002

Data Index: 914247 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0378. Min Act: -0.0002

Data Index: 821304 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1074152 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0378. Min Act: -0.0003

Data Index: 691049 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1152473 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0381. Min Act: -0.0003

Data Index: 425900 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0375. Min Act: -0.0002

Data Index: 546937 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1349721 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0366. Min Act: -0.0003

Data Index: 1253833 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0369. Min Act: -0.0003

Data Index: 468639 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0363. Min Act: -0.0002

Data Index: 646909 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0359. Min Act: -0.0002

Data Index: 467796 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0366. Min Act: -0.0003

Data Index: 57888 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1223648 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0358. Min Act: -0.0003

Data Index: 21435 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0354. Min Act: -0.0003

Data Index: 653042 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0350. Min Act: -0.0003

Data Index: 749796 (C4 (Web Text))

Max Activating Token Index: 355