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

Dataset: The Pile

Neuron 3243 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0299. Min Range: -1.0299

Max Act: 1.0211. Min Act: -0.0000

Data Index: 586000 (The Pile)

Max Activating Token Index: 450

Text #1

Max Range: 1.0299. Min Range: -1.0299

Max Act: 1.0293. Min Act: -0.0000

Data Index: 336775 (The Pile)

Max Activating Token Index: 292

Text #2

Max Range: 1.0299. Min Range: -1.0299

Max Act: 1.0008. Min Act: -0.0000

Data Index: 710354 (The Pile)

Max Activating Token Index: 116

Text #3

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.9658. Min Act: -0.0000

Data Index: 1943678 (The Pile)

Max Activating Token Index: 670

Text #4

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.9527. Min Act: -0.0000

Data Index: 241094 (The Pile)

Max Activating Token Index: 303

Text #5

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1843814 (The Pile)

Max Activating Token Index: 813

Text #6

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.8614. Min Act: -0.0000

Data Index: 482358 (The Pile)

Max Activating Token Index: 650

Text #7

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.8435. Min Act: -0.0000

Data Index: 1547615 (The Pile)

Max Activating Token Index: 21

Text #8

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.8926. Min Act: -0.0000

Data Index: 736991 (The Pile)

Max Activating Token Index: 185

Text #9

Max Range: 1.0299. Min Range: -1.0299

Max Act: 1.0299. Min Act: -0.0000

Data Index: 511418 (The Pile)

Max Activating Token Index: 359

Text #10

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.9286. Min Act: -0.0000

Data Index: 1243460 (The Pile)

Max Activating Token Index: 753

Text #11

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1391381 (The Pile)

Max Activating Token Index: 21

Text #12

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.9676. Min Act: -0.0000

Data Index: 1249371 (The Pile)

Max Activating Token Index: 658

Text #13

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.9150. Min Act: -0.0000

Data Index: 352904 (The Pile)

Max Activating Token Index: 859

Text #14

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.8835. Min Act: -0.0000

Data Index: 618937 (The Pile)

Max Activating Token Index: 324

Text #15

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.8556. Min Act: -0.0000

Data Index: 1871291 (The Pile)

Max Activating Token Index: 634

Text #16

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1615328 (The Pile)

Max Activating Token Index: 113

Text #17

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.9750. Min Act: -0.0000

Data Index: 26446 (The Pile)

Max Activating Token Index: 220

Text #18

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.8174. Min Act: -0.0000

Data Index: 247636 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 1.0299. Min Range: -1.0299

Max Act: 0.8868. Min Act: -0.0000

Data Index: 985843 (The Pile)

Max Activating Token Index: 267