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

Dataset: The Pile

Neuron 1260 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: 1.7980. Min Range: -1.7980

Max Act: 1.7787. Min Act: -0.0000

Data Index: 276008 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.7980. Min Act: -0.0000

Data Index: 593940 (The Pile)

Max Activating Token Index: 974

Text #2

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.5756. Min Act: -0.0000

Data Index: 130863 (The Pile)

Max Activating Token Index: 925

Text #3

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.4270. Min Act: -0.0000

Data Index: 1120172 (The Pile)

Max Activating Token Index: 922

Text #4

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.5618. Min Act: -0.0000

Data Index: 860072 (The Pile)

Max Activating Token Index: 971

Text #5

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.7557. Min Act: -0.0000

Data Index: 1694150 (The Pile)

Max Activating Token Index: 259

Text #6

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.4580. Min Act: -0.0000

Data Index: 911440 (The Pile)

Max Activating Token Index: 578

Text #7

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.6357. Min Act: -0.0000

Data Index: 352297 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.6208. Min Act: -0.0000

Data Index: 431785 (The Pile)

Max Activating Token Index: 982

Text #9

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.5932. Min Act: -0.0000

Data Index: 586248 (The Pile)

Max Activating Token Index: 919

Text #10

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.6558. Min Act: -0.0000

Data Index: 338151 (The Pile)

Max Activating Token Index: 84

Text #11

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.5551. Min Act: -0.0000

Data Index: 1660128 (The Pile)

Max Activating Token Index: 428

Text #12

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.6338. Min Act: -0.0000

Data Index: 820516 (The Pile)

Max Activating Token Index: 21

Text #13

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.4646. Min Act: -0.0000

Data Index: 121665 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.6391. Min Act: -0.0000

Data Index: 1757606 (The Pile)

Max Activating Token Index: 972

Text #15

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.5198. Min Act: -0.0000

Data Index: 527501 (The Pile)

Max Activating Token Index: 238

Text #16

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.5681. Min Act: -0.0000

Data Index: 759529 (The Pile)

Max Activating Token Index: 291

Text #17

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.5725. Min Act: -0.0000

Data Index: 266570 (The Pile)

Max Activating Token Index: 142

Text #18

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.5716. Min Act: -0.0000

Data Index: 1367401 (The Pile)

Max Activating Token Index: 425

Text #19

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.4767. Min Act: -0.0000

Data Index: 207344 (The Pile)

Max Activating Token Index: 526