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

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

Neuron 3606 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0332. Min Act: -0.0001

Data Index: 503958 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1083473 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0307. Min Act: -0.0001

Data Index: 1080270 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0285. Min Act: -0.0001

Data Index: 69975 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0296. Min Act: -0.0001

Data Index: 1126072 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0290. Min Act: -0.0001

Data Index: 1194218 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0297. Min Act: -0.0001

Data Index: 596183 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0286. Min Act: -0.0001

Data Index: 1120894 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0275. Min Act: -0.0001

Data Index: 200951 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0263. Min Act: -0.0001

Data Index: 228216 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0247. Min Act: -0.0001

Data Index: 938524 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0286. Min Act: -0.0001

Data Index: 324516 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0287. Min Act: -0.0001

Data Index: 257596 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1076603 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0260. Min Act: -0.0001

Data Index: 89653 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0266. Min Act: -0.0001

Data Index: 55405 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0267. Min Act: -0.0001

Data Index: 91790 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0259. Min Act: -0.0001

Data Index: 195078 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0246. Min Act: -0.0001

Data Index: 100543 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0267. Min Act: -0.0001

Data Index: 121002 (C4 (Web Text))

Max Activating Token Index: 952