Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 19 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0006

Data Index: 442040 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0456. Min Act: -0.0006

Data Index: 252945 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0410. Min Act: -0.0006

Data Index: 50120 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0415. Min Act: -0.0006

Data Index: 1204010 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0388. Min Act: -0.0006

Data Index: 916234 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0375. Min Act: -0.0006

Data Index: 1298181 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0384. Min Act: -0.0006

Data Index: 116281 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0375. Min Act: -0.0006

Data Index: 134846 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0363. Min Act: -0.0006

Data Index: 972705 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0329. Min Act: -0.0006

Data Index: 174336 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0320. Min Act: -0.0006

Data Index: 907814 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0365. Min Act: -0.0006

Data Index: 1129049 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0321. Min Act: -0.0006

Data Index: 207988 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0391. Min Act: -0.0006

Data Index: 1151775 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0353. Min Act: -0.0006

Data Index: 1312227 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0290. Min Act: -0.0006

Data Index: 719385 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0379. Min Act: -0.0006

Data Index: 393975 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0379. Min Act: -0.0006

Data Index: 1329130 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0368. Min Act: -0.0006

Data Index: 1099004 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0360. Min Act: -0.0006

Data Index: 575106 (C4 (Web Text))

Max Activating Token Index: 999