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

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

Neuron 3720 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1021222 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1359634 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0505. Min Act: -0.0002

Data Index: 107156 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0464. Min Act: -0.0003

Data Index: 1063622 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1627100 (Python Code)

Max Activating Token Index: 578

Text #5

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1026169 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0514. Min Act: -0.0003

Data Index: 583640 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0451. Min Act: -0.0003

Data Index: 958288 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0483. Min Act: -0.0002

Data Index: 234702 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0442. Min Act: -0.0002

Data Index: 145565 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0431. Min Act: -0.0002

Data Index: 564814 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0467. Min Act: -0.0003

Data Index: 819647 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1524643 (Python Code)

Max Activating Token Index: 775

Text #13

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0395. Min Act: -0.0002

Data Index: 6759 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0457. Min Act: -0.0002

Data Index: 221293 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0437. Min Act: -0.0003

Data Index: 1326960 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1275083 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0392. Min Act: -0.0003

Data Index: 1642113 (Python Code)

Max Activating Token Index: 479

Text #18

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1621962 (Python Code)

Max Activating Token Index: 575

Text #19

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1507451 (Python Code)

Max Activating Token Index: 452