Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1719 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.4220. Min Act: -0.0002

Data Index: 747799 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.4051. Min Act: -0.0002

Data Index: 314113 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3886. Min Act: -0.0002

Data Index: 957281 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3790. Min Act: -0.0002

Data Index: 418307 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3605. Min Act: -0.0002

Data Index: 459102 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3699. Min Act: -0.0002

Data Index: 1108821 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3548. Min Act: -0.0002

Data Index: 667509 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3441. Min Act: -0.0002

Data Index: 463343 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3418. Min Act: -0.0002

Data Index: 909921 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3403. Min Act: -0.0002

Data Index: 791641 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3507. Min Act: -0.0002

Data Index: 570199 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3405. Min Act: -0.0002

Data Index: 601376 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3395. Min Act: -0.0002

Data Index: 549475 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3259. Min Act: -0.0002

Data Index: 674887 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3132. Min Act: -0.0002

Data Index: 904783 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3257. Min Act: -0.0002

Data Index: 1258283 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3213. Min Act: -0.0002

Data Index: 186886 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3140. Min Act: -0.0002

Data Index: 200827 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3172. Min Act: -0.0002

Data Index: 212032 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3107. Min Act: -0.0002

Data Index: 1145746 (C4 (Web Text))

Max Activating Token Index: 317