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

Dataset: The Pile

Neuron 1900 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4579. Min Range: -1.4579

Max Act: 1.4579. Min Act: -0.0000

Data Index: 1994432 (The Pile)

Max Activating Token Index: 419

Text #1

Max Range: 1.4579. Min Range: -1.4579

Max Act: 1.2163. Min Act: -0.0000

Data Index: 359214 (The Pile)

Max Activating Token Index: 146

Text #2

Max Range: 1.4579. Min Range: -1.4579

Max Act: 1.2241. Min Act: -0.0000

Data Index: 751716 (The Pile)

Max Activating Token Index: 199

Text #3

Max Range: 1.4579. Min Range: -1.4579

Max Act: 1.1321. Min Act: -0.0000

Data Index: 1613089 (The Pile)

Max Activating Token Index: 997

Text #4

Max Range: 1.4579. Min Range: -1.4579

Max Act: 1.0994. Min Act: -0.0000

Data Index: 1320621 (The Pile)

Max Activating Token Index: 133

Text #5

Max Range: 1.4579. Min Range: -1.4579

Max Act: 1.1322. Min Act: -0.0000

Data Index: 1138949 (The Pile)

Max Activating Token Index: 680

Text #6

Max Range: 1.4579. Min Range: -1.4579

Max Act: 1.0721. Min Act: -0.0000

Data Index: 1413195 (The Pile)

Max Activating Token Index: 482

Text #7

Max Range: 1.4579. Min Range: -1.4579

Max Act: 0.9694. Min Act: -0.0000

Data Index: 411360 (The Pile)

Max Activating Token Index: 844

Text #8

Max Range: 1.4579. Min Range: -1.4579

Max Act: 1.0483. Min Act: -0.0000

Data Index: 1598700 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 1.4579. Min Range: -1.4579

Max Act: 0.9257. Min Act: -0.0000

Data Index: 1979599 (The Pile)

Max Activating Token Index: 422

Text #10

Max Range: 1.4579. Min Range: -1.4579

Max Act: 0.9620. Min Act: -0.0000

Data Index: 1868234 (The Pile)

Max Activating Token Index: 666

Text #11

Max Range: 1.4579. Min Range: -1.4579

Max Act: 0.8146. Min Act: -0.0000

Data Index: 1408570 (The Pile)

Max Activating Token Index: 400

Text #12

Max Range: 1.4579. Min Range: -1.4579

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1209510 (The Pile)

Max Activating Token Index: 574

Text #13

Max Range: 1.4579. Min Range: -1.4579

Max Act: 0.9265. Min Act: -0.0000

Data Index: 1967932 (The Pile)

Max Activating Token Index: 995

Text #14

Max Range: 1.4579. Min Range: -1.4579

Max Act: 0.8622. Min Act: -0.0000

Data Index: 493250 (The Pile)

Max Activating Token Index: 581

Text #15

Max Range: 1.4579. Min Range: -1.4579

Max Act: 0.9505. Min Act: -0.0000

Data Index: 292791 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 1.4579. Min Range: -1.4579

Max Act: 0.8624. Min Act: -0.0000

Data Index: 245732 (The Pile)

Max Activating Token Index: 1002

Text #17

Max Range: 1.4579. Min Range: -1.4579

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1988925 (The Pile)

Max Activating Token Index: 612

Text #18

Max Range: 1.4579. Min Range: -1.4579

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1565401 (The Pile)

Max Activating Token Index: 814

Text #19

Max Range: 1.4579. Min Range: -1.4579

Max Act: 0.7733. Min Act: -0.0000

Data Index: 1988853 (The Pile)

Max Activating Token Index: 925