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

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

Neuron 2524 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5625. Min Range: -1.5625

Max Act: 1.5625. Min Act: -0.0000

Data Index: 1643564 (Python Code)

Max Activating Token Index: 920

Text #1

Max Range: 1.5625. Min Range: -1.5625

Max Act: 1.3016. Min Act: -0.0000

Data Index: 1450389 (Python Code)

Max Activating Token Index: 956

Text #2

Max Range: 1.5625. Min Range: -1.5625

Max Act: 1.2200. Min Act: 0.0000

Data Index: 1387815 (Python Code)

Max Activating Token Index: 730

Text #3

Max Range: 1.5625. Min Range: -1.5625

Max Act: 1.1127. Min Act: -0.0000

Data Index: 1367382 (Python Code)

Max Activating Token Index: 635

Text #4

Max Range: 1.5625. Min Range: -1.5625

Max Act: 1.1052. Min Act: -0.0000

Data Index: 1600781 (Python Code)

Max Activating Token Index: 85

Text #5

Max Range: 1.5625. Min Range: -1.5625

Max Act: 1.1022. Min Act: -0.0000

Data Index: 1579473 (Python Code)

Max Activating Token Index: 33

Text #6

Max Range: 1.5625. Min Range: -1.5625

Max Act: 1.0821. Min Act: -0.0000

Data Index: 1391036 (Python Code)

Max Activating Token Index: 507

Text #7

Max Range: 1.5625. Min Range: -1.5625

Max Act: 1.0611. Min Act: -0.0000

Data Index: 1619694 (Python Code)

Max Activating Token Index: 326

Text #8

Max Range: 1.5625. Min Range: -1.5625

Max Act: 1.1170. Min Act: -0.0000

Data Index: 1634864 (Python Code)

Max Activating Token Index: 471

Text #9

Max Range: 1.5625. Min Range: -1.5625

Max Act: 1.0890. Min Act: 0.0000

Data Index: 1634844 (Python Code)

Max Activating Token Index: 196

Text #10

Max Range: 1.5625. Min Range: -1.5625

Max Act: 0.9914. Min Act: -0.0000

Data Index: 1529975 (Python Code)

Max Activating Token Index: 65

Text #11

Max Range: 1.5625. Min Range: -1.5625

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1490681 (Python Code)

Max Activating Token Index: 368

Text #12

Max Range: 1.5625. Min Range: -1.5625

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1596762 (Python Code)

Max Activating Token Index: 391

Text #13

Max Range: 1.5625. Min Range: -1.5625

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1639762 (Python Code)

Max Activating Token Index: 646

Text #14

Max Range: 1.5625. Min Range: -1.5625

Max Act: 1.0120. Min Act: -0.0000

Data Index: 1587452 (Python Code)

Max Activating Token Index: 506

Text #15

Max Range: 1.5625. Min Range: -1.5625

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1438535 (Python Code)

Max Activating Token Index: 449

Text #16

Max Range: 1.5625. Min Range: -1.5625

Max Act: 0.9424. Min Act: -0.0000

Data Index: 1594779 (Python Code)

Max Activating Token Index: 208

Text #17

Max Range: 1.5625. Min Range: -1.5625

Max Act: 0.9169. Min Act: -0.0000

Data Index: 1244042 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 1.5625. Min Range: -1.5625

Max Act: 0.8785. Min Act: -0.0000

Data Index: 610506 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 1.5625. Min Range: -1.5625

Max Act: 0.8494. Min Act: -0.0000

Data Index: 1452752 (Python Code)

Max Activating Token Index: 264