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

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

Neuron 1250 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: 0.0598. Min Range: -0.0598

Max Act: 0.0598. Min Act: -0.0004

Data Index: 1298973 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1275470 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0569. Min Act: -0.0003

Data Index: 506744 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0540. Min Act: -0.0004

Data Index: 875270 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0518. Min Act: -0.0000

Data Index: 1214597 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0507. Min Act: -0.0002

Data Index: 436629 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0489. Min Act: -0.0004

Data Index: 146481 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1354123 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0483. Min Act: -0.0003

Data Index: 275353 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1254682 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0459. Min Act: -0.0002

Data Index: 399521 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1236571 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0451. Min Act: -0.0003

Data Index: 575875 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0436. Min Act: -0.0003

Data Index: 970812 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0441. Min Act: -0.0003

Data Index: 696994 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0407. Min Act: -0.0003

Data Index: 870815 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0429. Min Act: -0.0001

Data Index: 108347 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0422. Min Act: -0.0003

Data Index: 601604 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0420. Min Act: -0.0003

Data Index: 1167195 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0422. Min Act: -0.0003

Data Index: 1193376 (C4 (Web Text))

Max Activating Token Index: 688