Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 454 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0461. Min Act: -0.0006

Data Index: 411062 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0447. Min Act: -0.0006

Data Index: 603658 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0431. Min Act: -0.0006

Data Index: 390091 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0437. Min Act: -0.0006

Data Index: 595344 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0435. Min Act: -0.0006

Data Index: 1264712 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0432. Min Act: -0.0006

Data Index: 409606 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0416. Min Act: -0.0006

Data Index: 261404 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0406. Min Act: -0.0006

Data Index: 70525 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0413. Min Act: -0.0006

Data Index: 890144 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0413. Min Act: -0.0006

Data Index: 412996 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0411. Min Act: -0.0006

Data Index: 960946 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0411. Min Act: -0.0006

Data Index: 691242 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0403. Min Act: -0.0006

Data Index: 684201 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0409. Min Act: -0.0006

Data Index: 37120 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0410. Min Act: -0.0006

Data Index: 1094355 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0406. Min Act: -0.0006

Data Index: 1348539 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0415. Min Act: -0.0006

Data Index: 144929 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0395. Min Act: -0.0006

Data Index: 307151 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0397. Min Act: -0.0006

Data Index: 212206 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0402. Min Act: -0.0006

Data Index: 1268117 (C4 (Web Text))

Max Activating Token Index: 239