Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 558 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3575. Min Act: -0.0005

Data Index: 40031 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3561. Min Act: -0.0004

Data Index: 577026 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3518. Min Act: -0.0004

Data Index: 496931 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3377. Min Act: -0.0005

Data Index: 1289810 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3465. Min Act: -0.0005

Data Index: 509830 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3450. Min Act: -0.0004

Data Index: 1043559 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3456. Min Act: -0.0004

Data Index: 527458 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3428. Min Act: -0.0004

Data Index: 1164946 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3346. Min Act: -0.0005

Data Index: 364362 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3290. Min Act: -0.0004

Data Index: 1045232 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3201. Min Act: -0.0004

Data Index: 1070765 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3188. Min Act: -0.0004

Data Index: 432212 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3138. Min Act: -0.0004

Data Index: 624347 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3141. Min Act: -0.0004

Data Index: 1068222 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3132. Min Act: -0.0005

Data Index: 898135 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3113. Min Act: -0.0004

Data Index: 287052 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3003. Min Act: -0.0004

Data Index: 206821 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3002. Min Act: -0.0004

Data Index: 366471 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3102. Min Act: -0.0004

Data Index: 667252 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2990. Min Act: -0.0004

Data Index: 392815 (C4 (Web Text))

Max Activating Token Index: 449