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

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

Neuron 988 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.6383. Min Act: -0.0000

Data Index: 1080032 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.3381. Min Act: -0.0000

Data Index: 1014367 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.3167. Min Act: -0.0000

Data Index: 491908 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.3026. Min Act: -0.0000

Data Index: 1006716 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.2584. Min Act: -0.0000

Data Index: 289636 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.3878. Min Act: -0.0000

Data Index: 1179613 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.2394. Min Act: -0.0000

Data Index: 397212 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.1676. Min Act: -0.0000

Data Index: 103127 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.1559. Min Act: -0.0000

Data Index: 1038516 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.1725. Min Act: -0.0000

Data Index: 286900 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1034330 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.0506. Min Act: -0.0000

Data Index: 706028 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.1215. Min Act: -0.0000

Data Index: 696196 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.2017. Min Act: -0.0000

Data Index: 720897 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.0726. Min Act: -0.0000

Data Index: 519258 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.0119. Min Act: -0.0000

Data Index: 802655 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.1212. Min Act: -0.0000

Data Index: 411652 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.0818. Min Act: -0.0000

Data Index: 1331022 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.1002. Min Act: -0.0000

Data Index: 1240747 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.0865. Min Act: -0.0000

Data Index: 44702 (C4 (Web Text))

Max Activating Token Index: 755