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

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

Neuron 3650 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1962. Min Act: -0.0002

Data Index: 891786 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.2153. Min Act: -0.0002

Data Index: 77505 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1821. Min Act: -0.0002

Data Index: 976393 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1750. Min Act: -0.0002

Data Index: 267967 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1803. Min Act: -0.0002

Data Index: 1239037 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1624. Min Act: -0.0002

Data Index: 957711 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1640. Min Act: -0.0002

Data Index: 1076905 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1656. Min Act: -0.0002

Data Index: 561579 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1458. Min Act: -0.0002

Data Index: 198792 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1343. Min Act: -0.0002

Data Index: 341107 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1456. Min Act: -0.0002

Data Index: 171174 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1664. Min Act: -0.0002

Data Index: 977274 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1533. Min Act: -0.0002

Data Index: 1244426 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1419. Min Act: -0.0002

Data Index: 745085 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1628. Min Act: -0.0002

Data Index: 1334129 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1459. Min Act: -0.0002

Data Index: 920235 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1472. Min Act: -0.0002

Data Index: 392947 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1467. Min Act: -0.0002

Data Index: 1217466 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1543. Min Act: -0.0002

Data Index: 1343459 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1150. Min Act: -0.0002

Data Index: 31488 (C4 (Web Text))

Max Activating Token Index: 285