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

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

Neuron 2352 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.3215. Min Act: -0.0001

Data Index: 897635 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.3112. Min Act: -0.0001

Data Index: 387268 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2871. Min Act: -0.0001

Data Index: 1034662 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2720. Min Act: -0.0001

Data Index: 871408 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2683. Min Act: -0.0001

Data Index: 379728 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2533. Min Act: -0.0001

Data Index: 163459 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2473. Min Act: -0.0000

Data Index: 486731 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2463. Min Act: -0.0001

Data Index: 168568 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2451. Min Act: -0.0001

Data Index: 437136 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2599. Min Act: -0.0001

Data Index: 1170032 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2186. Min Act: -0.0001

Data Index: 878003 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2061. Min Act: -0.0001

Data Index: 1353811 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2103. Min Act: -0.0001

Data Index: 1152946 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2118. Min Act: -0.0001

Data Index: 423277 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2038. Min Act: -0.0001

Data Index: 941337 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2312. Min Act: -0.0001

Data Index: 1191073 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2094. Min Act: -0.0001

Data Index: 1140438 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2190. Min Act: -0.0001

Data Index: 99122 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2181. Min Act: -0.0001

Data Index: 364380 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2006. Min Act: -0.0001

Data Index: 175117 (C4 (Web Text))

Max Activating Token Index: 397