Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4734 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.4383. Min Range: -3.4383

Max Act: 3.4383. Min Act: -0.0000

Data Index: 639244 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 3.4383. Min Range: -3.4383

Max Act: 2.7072. Min Act: -0.0000

Data Index: 180185 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 3.4383. Min Range: -3.4383

Max Act: 2.8160. Min Act: -0.0000

Data Index: 152011 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 3.4383. Min Range: -3.4383

Max Act: 2.4473. Min Act: -0.0000

Data Index: 1013291 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 3.4383. Min Range: -3.4383

Max Act: 2.4236. Min Act: -0.0000

Data Index: 460662 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 3.4383. Min Range: -3.4383

Max Act: 2.2651. Min Act: -0.0000

Data Index: 698925 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 3.4383. Min Range: -3.4383

Max Act: 2.3565. Min Act: -0.0000

Data Index: 717526 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 3.4383. Min Range: -3.4383

Max Act: 2.1897. Min Act: -0.0000

Data Index: 711073 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 3.4383. Min Range: -3.4383

Max Act: 1.9348. Min Act: -0.0000

Data Index: 1022361 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 3.4383. Min Range: -3.4383

Max Act: 2.2411. Min Act: -0.0000

Data Index: 1068806 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 3.4383. Min Range: -3.4383

Max Act: 1.9883. Min Act: -0.0000

Data Index: 117486 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 3.4383. Min Range: -3.4383

Max Act: 1.9993. Min Act: -0.0000

Data Index: 1217199 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 3.4383. Min Range: -3.4383

Max Act: 2.0504. Min Act: -0.0000

Data Index: 811900 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 3.4383. Min Range: -3.4383

Max Act: 2.1247. Min Act: -0.0000

Data Index: 551894 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 3.4383. Min Range: -3.4383

Max Act: 2.0234. Min Act: -0.0000

Data Index: 343507 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 3.4383. Min Range: -3.4383

Max Act: 1.8425. Min Act: -0.0000

Data Index: 969363 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 3.4383. Min Range: -3.4383

Max Act: 1.8487. Min Act: -0.0000

Data Index: 14098 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 3.4383. Min Range: -3.4383

Max Act: 1.8355. Min Act: -0.0000

Data Index: 315427 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 3.4383. Min Range: -3.4383

Max Act: 1.7421. Min Act: -0.0000

Data Index: 1064685 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 3.4383. Min Range: -3.4383

Max Act: 1.9387. Min Act: -0.0000

Data Index: 937069 (C4 (Web Text))

Max Activating Token Index: 869