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

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

Neuron 4321 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.7169. Min Act: 0.0000

Data Index: 889017 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6884. Min Act: -0.0000

Data Index: 95675 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.7082. Min Act: 0.0000

Data Index: 1142461 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1163937 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1203571 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6801. Min Act: -0.0000

Data Index: 883106 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1350129 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6371. Min Act: -0.0000

Data Index: 142194 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6571. Min Act: 0.0000

Data Index: 128324 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6815. Min Act: -0.0000

Data Index: 79764 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6482. Min Act: 0.0000

Data Index: 76635 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6517. Min Act: 0.0000

Data Index: 730766 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6312. Min Act: -0.0000

Data Index: 798091 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6351. Min Act: 0.0001

Data Index: 1001175 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6286. Min Act: 0.0000

Data Index: 327820 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6303. Min Act: 0.0000

Data Index: 979929 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6291. Min Act: -0.0000

Data Index: 189118 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6570. Min Act: 0.0000

Data Index: 398539 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6119. Min Act: 0.0001

Data Index: 1330407 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6275. Min Act: -0.0000

Data Index: 6456 (C4 (Web Text))

Max Activating Token Index: 625