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

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

Neuron 4618 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: 0.0549. Min Range: -0.0549

Max Act: 0.0549. Min Act: -0.0002

Data Index: 687693 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1577563 (Python Code)

Max Activating Token Index: 87

Text #2

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1387826 (Python Code)

Max Activating Token Index: 212

Text #3

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0506. Min Act: -0.0002

Data Index: 852808 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0455. Min Act: -0.0002

Data Index: 961808 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1190342 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1439506 (Python Code)

Max Activating Token Index: 201

Text #7

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1560058 (Python Code)

Max Activating Token Index: 338

Text #8

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0468. Min Act: -0.0002

Data Index: 846107 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0492. Min Act: -0.0002

Data Index: 341364 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1407151 (Python Code)

Max Activating Token Index: 862

Text #11

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0424. Min Act: -0.0002

Data Index: 290051 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1537430 (Python Code)

Max Activating Token Index: 457

Text #13

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1358328 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0426. Min Act: -0.0002

Data Index: 667179 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1595148 (Python Code)

Max Activating Token Index: 714

Text #16

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0459. Min Act: -0.0002

Data Index: 292599 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1605198 (Python Code)

Max Activating Token Index: 762

Text #18

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1650643 (Python Code)

Max Activating Token Index: 291

Text #19

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0452. Min Act: -0.0002

Data Index: 601893 (C4 (Web Text))

Max Activating Token Index: 814