Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5294 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0658. Min Act: -0.0000

Data Index: 414733 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0610. Min Act: -0.0000

Data Index: 1282245 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0570. Min Act: -0.0000

Data Index: 829420 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0494. Min Act: -0.0000

Data Index: 563993 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0558. Min Act: -0.0000

Data Index: 452335 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0617. Min Act: -0.0000

Data Index: 148130 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0471. Min Act: -0.0000

Data Index: 1419261 (Python Code)

Max Activating Token Index: 729

Text #7

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0483. Min Act: -0.0000

Data Index: 1067117 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0451. Min Act: -0.0000

Data Index: 196653 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0470. Min Act: -0.0000

Data Index: 353264 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0455. Min Act: -0.0000

Data Index: 505468 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0422. Min Act: -0.0000

Data Index: 6784 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0482. Min Act: -0.0000

Data Index: 245494 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0448. Min Act: -0.0000

Data Index: 1025111 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1562693 (Python Code)

Max Activating Token Index: 854

Text #15

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0454. Min Act: -0.0000

Data Index: 1211121 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0457. Min Act: -0.0000

Data Index: 642829 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0436. Min Act: -0.0000

Data Index: 676397 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0374. Min Act: -0.0000

Data Index: 1052542 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0445. Min Act: -0.0000

Data Index: 687511 (C4 (Web Text))

Max Activating Token Index: 612