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

Dataset: The Pile

Neuron 1904 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.8724. Min Act: -0.0000

Data Index: 178624 (The Pile)

Max Activating Token Index: 665

Text #1

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.8586. Min Act: -0.0000

Data Index: 880135 (The Pile)

Max Activating Token Index: 124

Text #2

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.8284. Min Act: -0.0000

Data Index: 1505975 (The Pile)

Max Activating Token Index: 513

Text #3

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.8297. Min Act: -0.0000

Data Index: 507002 (The Pile)

Max Activating Token Index: 1004

Text #4

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7480. Min Act: -0.0000

Data Index: 907977 (The Pile)

Max Activating Token Index: 1022

Text #5

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7784. Min Act: -0.0000

Data Index: 633571 (The Pile)

Max Activating Token Index: 126

Text #6

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1707383 (The Pile)

Max Activating Token Index: 361

Text #7

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1074376 (The Pile)

Max Activating Token Index: 741

Text #8

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7067. Min Act: -0.0000

Data Index: 269057 (The Pile)

Max Activating Token Index: 105

Text #9

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1351064 (The Pile)

Max Activating Token Index: 81

Text #10

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1026208 (The Pile)

Max Activating Token Index: 281

Text #11

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1836636 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1155862 (The Pile)

Max Activating Token Index: 649

Text #13

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6236. Min Act: 0.0000

Data Index: 1258091 (The Pile)

Max Activating Token Index: 328

Text #14

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6032. Min Act: -0.0000

Data Index: 42332 (The Pile)

Max Activating Token Index: 161

Text #15

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6206. Min Act: -0.0000

Data Index: 865749 (The Pile)

Max Activating Token Index: 996

Text #16

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1345677 (The Pile)

Max Activating Token Index: 143

Text #17

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6308. Min Act: -0.0000

Data Index: 1126979 (The Pile)

Max Activating Token Index: 67

Text #18

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1086407 (The Pile)

Max Activating Token Index: 501

Text #19

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.5575. Min Act: -0.0000

Data Index: 430825 (The Pile)

Max Activating Token Index: 867