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

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

Neuron 3486 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: 0.8187. Min Range: -0.8187

Max Act: 0.8187. Min Act: -0.0001

Data Index: 121500 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6426. Min Act: -0.0001

Data Index: 1150505 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6922. Min Act: -0.0001

Data Index: 690281 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6489. Min Act: -0.0001

Data Index: 102288 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6617. Min Act: -0.0001

Data Index: 603303 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6400. Min Act: -0.0001

Data Index: 500392 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6019. Min Act: -0.0001

Data Index: 1289670 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5658. Min Act: -0.0001

Data Index: 1309375 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6013. Min Act: -0.0001

Data Index: 840123 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6002. Min Act: -0.0001

Data Index: 168603 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5809. Min Act: -0.0001

Data Index: 152151 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5873. Min Act: -0.0001

Data Index: 160268 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5677. Min Act: -0.0001

Data Index: 993924 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5771. Min Act: -0.0001

Data Index: 632743 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5632. Min Act: -0.0001

Data Index: 569585 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5763. Min Act: -0.0001

Data Index: 532947 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5566. Min Act: -0.0001

Data Index: 751123 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5304. Min Act: -0.0001

Data Index: 28494 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5663. Min Act: -0.0001

Data Index: 1325002 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5275. Min Act: -0.0001

Data Index: 889646 (C4 (Web Text))

Max Activating Token Index: 52