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

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

Neuron 1181 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: 0.0538. Min Range: -0.0538

Max Act: 0.0538. Min Act: -0.0005

Data Index: 640723 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0529. Min Act: -0.0006

Data Index: 695197 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0520. Min Act: -0.0006

Data Index: 102831 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0509. Min Act: -0.0006

Data Index: 483623 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0526. Min Act: -0.0006

Data Index: 1491042 (Python Code)

Max Activating Token Index: 361

Text #5

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0495. Min Act: -0.0006

Data Index: 157508 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0505. Min Act: -0.0005

Data Index: 996138 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0469. Min Act: -0.0006

Data Index: 1321076 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0461. Min Act: -0.0006

Data Index: 419779 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0467. Min Act: -0.0006

Data Index: 652046 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0482. Min Act: -0.0006

Data Index: 977612 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0482. Min Act: -0.0006

Data Index: 335404 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0465. Min Act: -0.0006

Data Index: 187094 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0482. Min Act: -0.0006

Data Index: 748709 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0473. Min Act: -0.0006

Data Index: 929371 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0488. Min Act: -0.0006

Data Index: 96276 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0488. Min Act: -0.0006

Data Index: 649527 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0477. Min Act: -0.0005

Data Index: 1165647 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0476. Min Act: -0.0006

Data Index: 402309 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0467. Min Act: -0.0005

Data Index: 948501 (C4 (Web Text))

Max Activating Token Index: 920