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

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

Neuron 3250 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.3020. Min Act: -0.0001

Data Index: 966178 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.3505. Min Act: -0.0001

Data Index: 507099 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.3484. Min Act: -0.0001

Data Index: 146457 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.3444. Min Act: -0.0001

Data Index: 379139 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.2448. Min Act: -0.0001

Data Index: 1170344 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.3851. Min Act: -0.0001

Data Index: 259472 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.2753. Min Act: -0.0001

Data Index: 1050643 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.2288. Min Act: -0.0001

Data Index: 1354119 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.1457. Min Act: -0.0001

Data Index: 832574 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.1681. Min Act: -0.0001

Data Index: 105693 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.2028. Min Act: -0.0001

Data Index: 897979 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.1435. Min Act: -0.0001

Data Index: 256399 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.0279. Min Act: -0.0001

Data Index: 105287 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.1312. Min Act: -0.0001

Data Index: 142701 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.0709. Min Act: -0.0001

Data Index: 1300293 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.0643. Min Act: -0.0001

Data Index: 1331256 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.0903. Min Act: -0.0001

Data Index: 921007 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.0404. Min Act: -0.0001

Data Index: 592014 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 1.3851. Min Range: -1.3851

Max Act: 1.0767. Min Act: -0.0001

Data Index: 1233865 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 1.3851. Min Range: -1.3851

Max Act: 0.9813. Min Act: -0.0001

Data Index: 308885 (C4 (Web Text))

Max Activating Token Index: 652