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

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

Neuron 3589 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: 0.0416. Min Range: -0.0416

Max Act: 0.0416. Min Act: -0.0003

Data Index: 90313 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0403. Min Act: -0.0003

Data Index: 756671 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0393. Min Act: -0.0003

Data Index: 516594 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0368. Min Act: -0.0003

Data Index: 834742 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0370. Min Act: -0.0003

Data Index: 340977 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0353. Min Act: -0.0003

Data Index: 1204452 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0354. Min Act: -0.0003

Data Index: 893505 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0347. Min Act: -0.0003

Data Index: 926038 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1010212 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0354. Min Act: -0.0004

Data Index: 1277636 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1314092 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1198557 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0335. Min Act: -0.0003

Data Index: 709108 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0332. Min Act: -0.0003

Data Index: 533819 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0313. Min Act: -0.0003

Data Index: 652781 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0345. Min Act: -0.0003

Data Index: 276562 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0323. Min Act: -0.0003

Data Index: 252550 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0335. Min Act: -0.0003

Data Index: 749737 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1103793 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1094854 (C4 (Web Text))

Max Activating Token Index: 764