Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1141 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1690. Min Act: -0.0001

Data Index: 64916 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1521. Min Act: -0.0001

Data Index: 143176 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1578. Min Act: -0.0001

Data Index: 226973 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1675. Min Act: -0.0001

Data Index: 270458 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1575. Min Act: -0.0001

Data Index: 166856 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1696. Min Act: -0.0001

Data Index: 729996 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1540. Min Act: -0.0001

Data Index: 296464 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1619. Min Act: -0.0001

Data Index: 1054112 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1519. Min Act: -0.0001

Data Index: 206051 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1452. Min Act: -0.0001

Data Index: 407261 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1384. Min Act: -0.0001

Data Index: 952877 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1419. Min Act: -0.0001

Data Index: 604666 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1372. Min Act: -0.0001

Data Index: 1173069 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1380. Min Act: -0.0001

Data Index: 266036 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1298. Min Act: -0.0001

Data Index: 100251 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1543. Min Act: -0.0001

Data Index: 1318587 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1418. Min Act: -0.0001

Data Index: 805356 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1321. Min Act: -0.0001

Data Index: 954053 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1229536 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1384. Min Act: -0.0001

Data Index: 1101506 (C4 (Web Text))

Max Activating Token Index: 35