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

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

Neuron 2486 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2398. Min Act: -0.0001

Data Index: 112288 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2051. Min Act: -0.0001

Data Index: 439036 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1748. Min Act: -0.0001

Data Index: 281829 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1734. Min Act: -0.0001

Data Index: 335987 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1758. Min Act: -0.0001

Data Index: 164857 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1421. Min Act: -0.0001

Data Index: 829346 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1381. Min Act: -0.0001

Data Index: 229247 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1468. Min Act: -0.0001

Data Index: 907384 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1385. Min Act: -0.0001

Data Index: 960836 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1367. Min Act: -0.0001

Data Index: 892268 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1308. Min Act: -0.0001

Data Index: 902073 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1265. Min Act: -0.0001

Data Index: 322871 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1279. Min Act: -0.0001

Data Index: 540126 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1264. Min Act: -0.0001

Data Index: 99269 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1325. Min Act: -0.0001

Data Index: 176685 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1288. Min Act: -0.0001

Data Index: 360523 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1129183 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1327. Min Act: -0.0001

Data Index: 7467 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1207. Min Act: -0.0001

Data Index: 221056 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1223. Min Act: -0.0001

Data Index: 453895 (C4 (Web Text))

Max Activating Token Index: 259