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

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

Neuron 4496 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1396374 (Python Code)

Max Activating Token Index: 630

Text #1

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1591950 (Python Code)

Max Activating Token Index: 150

Text #2

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1627483 (Python Code)

Max Activating Token Index: 312

Text #3

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3431. Min Act: 0.0000

Data Index: 1568504 (Python Code)

Max Activating Token Index: 450

Text #4

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3315. Min Act: -0.0000

Data Index: 1504888 (Python Code)

Max Activating Token Index: 335

Text #5

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1388888 (Python Code)

Max Activating Token Index: 406

Text #6

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3055. Min Act: -0.0001

Data Index: 1408967 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2721. Min Act: -0.0000

Data Index: 1425152 (Python Code)

Max Activating Token Index: 193

Text #8

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2725. Min Act: 0.0000

Data Index: 1576815 (Python Code)

Max Activating Token Index: 340

Text #9

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2578. Min Act: 0.0001

Data Index: 1424227 (Python Code)

Max Activating Token Index: 483

Text #10

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1482401 (Python Code)

Max Activating Token Index: 618

Text #11

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2296. Min Act: -0.0000

Data Index: 1493147 (Python Code)

Max Activating Token Index: 677

Text #12

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1419507 (Python Code)

Max Activating Token Index: 385

Text #13

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2662. Min Act: 0.0001

Data Index: 1594744 (Python Code)

Max Activating Token Index: 220

Text #14

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2559. Min Act: 0.0000

Data Index: 1518686 (Python Code)

Max Activating Token Index: 363

Text #15

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2564. Min Act: 0.0000

Data Index: 1615704 (Python Code)

Max Activating Token Index: 457

Text #16

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1515670 (Python Code)

Max Activating Token Index: 74

Text #17

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1384397 (Python Code)

Max Activating Token Index: 980

Text #18

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1469131 (Python Code)

Max Activating Token Index: 424

Text #19

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1521386 (Python Code)

Max Activating Token Index: 178