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

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

Neuron 659 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1492. Min Act: -0.0003

Data Index: 855104 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1496. Min Act: -0.0003

Data Index: 264529 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1402. Min Act: -0.0003

Data Index: 165059 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1455. Min Act: -0.0003

Data Index: 770069 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1452. Min Act: -0.0003

Data Index: 466941 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1398. Min Act: -0.0003

Data Index: 839510 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1386. Min Act: -0.0003

Data Index: 198162 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1394. Min Act: -0.0003

Data Index: 1011852 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1430. Min Act: -0.0003

Data Index: 293485 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1326. Min Act: -0.0003

Data Index: 1110995 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1420. Min Act: -0.0003

Data Index: 1066362 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1419. Min Act: -0.0004

Data Index: 1050228 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1364. Min Act: -0.0003

Data Index: 1238810 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1353. Min Act: -0.0003

Data Index: 16683 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1459. Min Act: -0.0003

Data Index: 710511 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1384. Min Act: -0.0003

Data Index: 447849 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1382. Min Act: -0.0003

Data Index: 382076 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1428. Min Act: -0.0003

Data Index: 1288954 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1372. Min Act: -0.0003

Data Index: 1118645 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1371. Min Act: -0.0003

Data Index: 1155614 (C4 (Web Text))

Max Activating Token Index: 99