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

Dataset: The Pile

Neuron 108 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: 1.8311. Min Range: -1.8311

Max Act: 1.8311. Min Act: -0.0000

Data Index: 719134 (The Pile)

Max Activating Token Index: 918

Text #1

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.6284. Min Act: -0.0000

Data Index: 658702 (The Pile)

Max Activating Token Index: 679

Text #2

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.5186. Min Act: -0.0000

Data Index: 1670054 (The Pile)

Max Activating Token Index: 518

Text #3

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.4893. Min Act: -0.0000

Data Index: 1664781 (The Pile)

Max Activating Token Index: 124

Text #4

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.4819. Min Act: -0.0000

Data Index: 1955517 (The Pile)

Max Activating Token Index: 976

Text #5

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.4720. Min Act: -0.0000

Data Index: 987323 (The Pile)

Max Activating Token Index: 347

Text #6

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.3125. Min Act: -0.0000

Data Index: 1019328 (The Pile)

Max Activating Token Index: 968

Text #7

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.4474. Min Act: -0.0000

Data Index: 1920474 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.4447. Min Act: -0.0000

Data Index: 1487708 (The Pile)

Max Activating Token Index: 372

Text #9

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.5158. Min Act: -0.0000

Data Index: 1567616 (The Pile)

Max Activating Token Index: 432

Text #10

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.4282. Min Act: -0.0000

Data Index: 1316095 (The Pile)

Max Activating Token Index: 65

Text #11

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.4230. Min Act: -0.0000

Data Index: 846264 (The Pile)

Max Activating Token Index: 299

Text #12

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.5151. Min Act: -0.0000

Data Index: 106433 (The Pile)

Max Activating Token Index: 488

Text #13

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.5102. Min Act: -0.0000

Data Index: 1647181 (The Pile)

Max Activating Token Index: 604

Text #14

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.4165. Min Act: -0.0000

Data Index: 1021430 (The Pile)

Max Activating Token Index: 973

Text #15

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.4739. Min Act: -0.0000

Data Index: 1417781 (The Pile)

Max Activating Token Index: 460

Text #16

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.4382. Min Act: -0.0000

Data Index: 923982 (The Pile)

Max Activating Token Index: 805

Text #17

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.3448. Min Act: -0.0000

Data Index: 1559287 (The Pile)

Max Activating Token Index: 19

Text #18

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.3465. Min Act: -0.0000

Data Index: 1392167 (The Pile)

Max Activating Token Index: 718

Text #19

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.3410. Min Act: -0.0000

Data Index: 621681 (The Pile)

Max Activating Token Index: 452