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

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

Neuron 4640 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.6047. Min Act: -0.0000

Data Index: 789885 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.6334. Min Act: -0.0000

Data Index: 149589 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5455. Min Act: -0.0000

Data Index: 1216997 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4861. Min Act: -0.0000

Data Index: 401792 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4861. Min Act: -0.0000

Data Index: 880410 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4837. Min Act: -0.0000

Data Index: 603238 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4820. Min Act: -0.0000

Data Index: 697991 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4745. Min Act: -0.0000

Data Index: 856414 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4682. Min Act: -0.0000

Data Index: 191186 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4517. Min Act: -0.0000

Data Index: 616882 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1332330 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4288. Min Act: -0.0000

Data Index: 582257 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1230533 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4218. Min Act: -0.0000

Data Index: 993851 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4293. Min Act: -0.0000

Data Index: 110024 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4262. Min Act: -0.0000

Data Index: 367879 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4293. Min Act: -0.0000

Data Index: 341611 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1216883 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1305036 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4215. Min Act: -0.0000

Data Index: 518396 (C4 (Web Text))

Max Activating Token Index: 980