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

Dataset: The Pile

Neuron 2388 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.6983. Min Act: -0.0000

Data Index: 809870 (The Pile)

Max Activating Token Index: 295

Text #1

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1725876 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.6282. Min Act: -0.0000

Data Index: 1523423 (The Pile)

Max Activating Token Index: 976

Text #3

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5791. Min Act: -0.0000

Data Index: 934681 (The Pile)

Max Activating Token Index: 476

Text #4

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5756. Min Act: -0.0000

Data Index: 418227 (The Pile)

Max Activating Token Index: 498

Text #5

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4866. Min Act: -0.0000

Data Index: 834971 (The Pile)

Max Activating Token Index: 108

Text #6

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5087. Min Act: -0.0000

Data Index: 389579 (The Pile)

Max Activating Token Index: 129

Text #7

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.6460. Min Act: -0.0000

Data Index: 417139 (The Pile)

Max Activating Token Index: 938

Text #8

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1984970 (The Pile)

Max Activating Token Index: 775

Text #9

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4883. Min Act: -0.0000

Data Index: 971197 (The Pile)

Max Activating Token Index: 497

Text #10

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4996. Min Act: -0.0000

Data Index: 1185001 (The Pile)

Max Activating Token Index: 94

Text #11

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4709. Min Act: -0.0000

Data Index: 78435 (The Pile)

Max Activating Token Index: 505

Text #12

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4294. Min Act: -0.0000

Data Index: 891466 (The Pile)

Max Activating Token Index: 93

Text #13

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1640314 (The Pile)

Max Activating Token Index: 168

Text #14

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.3926. Min Act: -0.0000

Data Index: 318506 (The Pile)

Max Activating Token Index: 989

Text #15

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4230. Min Act: -0.0000

Data Index: 84539 (The Pile)

Max Activating Token Index: 368

Text #16

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1838037 (The Pile)

Max Activating Token Index: 73

Text #17

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5016. Min Act: -0.0000

Data Index: 206032 (The Pile)

Max Activating Token Index: 898

Text #18

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1496350 (The Pile)

Max Activating Token Index: 344

Text #19

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4254. Min Act: -0.0000

Data Index: 745965 (The Pile)

Max Activating Token Index: 796