Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 482 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2485. Min Act: -0.0002

Data Index: 606656 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2141. Min Act: -0.0002

Data Index: 325734 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2113. Min Act: -0.0002

Data Index: 1247626 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.1953. Min Act: -0.0001

Data Index: 1090881 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.1925. Min Act: -0.0002

Data Index: 654184 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.1712. Min Act: -0.0001

Data Index: 689113 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.1577. Min Act: -0.0002

Data Index: 877331 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.1634. Min Act: -0.0002

Data Index: 1276747 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.1474. Min Act: -0.0002

Data Index: 932616 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.1490. Min Act: -0.0002

Data Index: 1234892 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.1423. Min Act: -0.0002

Data Index: 772450 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.1520. Min Act: -0.0002

Data Index: 383625 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.1520. Min Act: -0.0002

Data Index: 65624 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.1477. Min Act: -0.0002

Data Index: 866051 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.1501. Min Act: -0.0002

Data Index: 1340919 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.1479. Min Act: -0.0002

Data Index: 670786 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.1425. Min Act: -0.0001

Data Index: 1210403 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.1364. Min Act: -0.0002

Data Index: 1418 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.1444. Min Act: -0.0002

Data Index: 317652 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.1384. Min Act: -0.0002

Data Index: 347985 (C4 (Web Text))

Max Activating Token Index: 995