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

Dataset: The Pile

Neuron 781 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: 0.8297. Min Range: -0.8297

Max Act: 0.8297. Min Act: -0.0000

Data Index: 676573 (The Pile)

Max Activating Token Index: 507

Text #1

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7486. Min Act: -0.0000

Data Index: 1169155 (The Pile)

Max Activating Token Index: 464

Text #2

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1304321 (The Pile)

Max Activating Token Index: 1008

Text #3

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7705. Min Act: -0.0000

Data Index: 1877831 (The Pile)

Max Activating Token Index: 643

Text #4

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7332. Min Act: -0.0000

Data Index: 1841474 (The Pile)

Max Activating Token Index: 201

Text #5

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1183512 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1700919 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1098274 (The Pile)

Max Activating Token Index: 409

Text #8

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6967. Min Act: -0.0000

Data Index: 248982 (The Pile)

Max Activating Token Index: 584

Text #9

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1818691 (The Pile)

Max Activating Token Index: 572

Text #10

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6661. Min Act: -0.0000

Data Index: 1319375 (The Pile)

Max Activating Token Index: 631

Text #11

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6410. Min Act: -0.0000

Data Index: 367306 (The Pile)

Max Activating Token Index: 579

Text #12

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1938694 (The Pile)

Max Activating Token Index: 602

Text #13

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6740. Min Act: -0.0000

Data Index: 1095299 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1629893 (The Pile)

Max Activating Token Index: 794

Text #15

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6305. Min Act: -0.0000

Data Index: 1007851 (The Pile)

Max Activating Token Index: 875

Text #16

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6228. Min Act: -0.0000

Data Index: 531461 (The Pile)

Max Activating Token Index: 218

Text #17

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6362. Min Act: -0.0000

Data Index: 1638666 (The Pile)

Max Activating Token Index: 232

Text #18

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1094227 (The Pile)

Max Activating Token Index: 366

Text #19

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6747. Min Act: -0.0000

Data Index: 286968 (The Pile)

Max Activating Token Index: 559