Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3012 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.1025. Min Range: -2.1025

Max Act: 2.1025. Min Act: -0.0000

Data Index: 919495 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.9152. Min Act: -0.0001

Data Index: 763496 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.9659. Min Act: -0.0001

Data Index: 167473 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.9472. Min Act: -0.0001

Data Index: 412637 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.9196. Min Act: -0.0000

Data Index: 549253 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.9247. Min Act: -0.0000

Data Index: 165080 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.8118. Min Act: -0.0000

Data Index: 1030235 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.9079. Min Act: -0.0000

Data Index: 1094133 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.7673. Min Act: -0.0001

Data Index: 432468 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.6913. Min Act: -0.0000

Data Index: 774193 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.7351. Min Act: -0.0001

Data Index: 56006 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.7483. Min Act: -0.0000

Data Index: 20374 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.6954. Min Act: -0.0000

Data Index: 519353 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.6829. Min Act: -0.0000

Data Index: 856904 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.7295. Min Act: -0.0000

Data Index: 787140 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.6094. Min Act: -0.0001

Data Index: 73428 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.6365. Min Act: -0.0001

Data Index: 299962 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.6241. Min Act: -0.0000

Data Index: 691789 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.5408. Min Act: -0.0000

Data Index: 499416 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 2.1025. Min Range: -2.1025

Max Act: 1.6112. Min Act: -0.0000

Data Index: 58767 (C4 (Web Text))

Max Activating Token Index: 91