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

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

Neuron 953 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: 0.1751. Min Range: -0.1751

Max Act: 0.1751. Min Act: -0.0001

Data Index: 18201 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1620. Min Act: -0.0001

Data Index: 839858 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1435. Min Act: -0.0001

Data Index: 1160022 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1393. Min Act: -0.0001

Data Index: 228737 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1477. Min Act: -0.0001

Data Index: 642867 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1382. Min Act: -0.0001

Data Index: 1225583 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1382. Min Act: -0.0001

Data Index: 1057835 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1411. Min Act: -0.0001

Data Index: 379272 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1246. Min Act: -0.0001

Data Index: 1172360 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1495520 (Python Code)

Max Activating Token Index: 186

Text #10

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1305. Min Act: -0.0001

Data Index: 329776 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1229. Min Act: -0.0001

Data Index: 971590 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1367. Min Act: -0.0001

Data Index: 929214 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1254. Min Act: -0.0001

Data Index: 1069572 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1174. Min Act: -0.0001

Data Index: 168883 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1165. Min Act: -0.0001

Data Index: 535050 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1080. Min Act: -0.0001

Data Index: 444569 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1122. Min Act: -0.0001

Data Index: 897000 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1151. Min Act: -0.0001

Data Index: 332029 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1191. Min Act: -0.0001

Data Index: 970771 (C4 (Web Text))

Max Activating Token Index: 343