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

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

Neuron 1461 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1108780 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0495. Min Act: -0.0002

Data Index: 190749 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0496. Min Act: -0.0002

Data Index: 919575 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1040667 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0451. Min Act: -0.0002

Data Index: 624362 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0394. Min Act: -0.0002

Data Index: 600963 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0498. Min Act: -0.0002

Data Index: 173927 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0506. Min Act: -0.0002

Data Index: 326199 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0560. Min Act: -0.0002

Data Index: 320648 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1085778 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1139533 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0373. Min Act: -0.0002

Data Index: 517372 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0478. Min Act: -0.0002

Data Index: 665964 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1383087 (Python Code)

Max Activating Token Index: 514

Text #14

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0457. Min Act: -0.0002

Data Index: 375822 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0368. Min Act: -0.0002

Data Index: 903757 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0418. Min Act: -0.0002

Data Index: 726647 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0449. Min Act: -0.0002

Data Index: 657352 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0452. Min Act: -0.0002

Data Index: 981273 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1285130 (C4 (Web Text))

Max Activating Token Index: 14