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

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

Neuron 1003 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: 1.2213. Min Range: -1.2213

Max Act: 1.1325. Min Act: -0.0001

Data Index: 352894 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 1.2213. Min Range: -1.2213

Max Act: 1.0484. Min Act: -0.0001

Data Index: 240194 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 1.2213. Min Range: -1.2213

Max Act: 1.2213. Min Act: -0.0001

Data Index: 1251193 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9460. Min Act: -0.0001

Data Index: 608209 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 1.2213. Min Range: -1.2213

Max Act: 1.0493. Min Act: -0.0001

Data Index: 510062 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9707. Min Act: -0.0001

Data Index: 285716 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 1.2213. Min Range: -1.2213

Max Act: 1.0315. Min Act: -0.0001

Data Index: 908814 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9041. Min Act: -0.0001

Data Index: 1031557 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 1.2213. Min Range: -1.2213

Max Act: 1.0013. Min Act: -0.0001

Data Index: 231741 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9829. Min Act: -0.0001

Data Index: 164002 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9647. Min Act: -0.0001

Data Index: 670754 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9414. Min Act: -0.0001

Data Index: 460568 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9596. Min Act: -0.0001

Data Index: 824372 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.8745. Min Act: -0.0001

Data Index: 1193970 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9467. Min Act: -0.0001

Data Index: 117953 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9259. Min Act: -0.0001

Data Index: 1195402 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.7139. Min Act: -0.0001

Data Index: 66208 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9317. Min Act: -0.0001

Data Index: 1273797 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9520. Min Act: -0.0001

Data Index: 1314894 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.8778. Min Act: -0.0001

Data Index: 754791 (C4 (Web Text))

Max Activating Token Index: 323