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

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

Neuron 1421 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0644. Min Act: -0.0004

Data Index: 126521 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0598. Min Act: -0.0003

Data Index: 528889 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0583. Min Act: -0.0003

Data Index: 233095 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0561. Min Act: -0.0003

Data Index: 230732 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0563. Min Act: -0.0003

Data Index: 1402692 (Python Code)

Max Activating Token Index: 485

Text #5

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0550. Min Act: -0.0002

Data Index: 252292 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0546. Min Act: -0.0003

Data Index: 397430 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1236765 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0534. Min Act: -0.0003

Data Index: 327386 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0531. Min Act: -0.0003

Data Index: 601928 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0500. Min Act: -0.0003

Data Index: 993559 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0468. Min Act: -0.0003

Data Index: 551172 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0478. Min Act: -0.0003

Data Index: 88170 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0476. Min Act: -0.0003

Data Index: 230653 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0472. Min Act: -0.0003

Data Index: 18200 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0469. Min Act: -0.0002

Data Index: 360194 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0462. Min Act: -0.0003

Data Index: 230707 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0454. Min Act: -0.0003

Data Index: 374291 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0452. Min Act: -0.0003

Data Index: 471176 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1038226 (C4 (Web Text))

Max Activating Token Index: 872