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

Dataset: The Pile

Neuron 3609 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.8933. Min Act: -0.0000

Data Index: 590558 (The Pile)

Max Activating Token Index: 507

Text #1

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.4198. Min Act: -0.0000

Data Index: 997553 (The Pile)

Max Activating Token Index: 835

Text #2

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.7357. Min Act: -0.0000

Data Index: 1974551 (The Pile)

Max Activating Token Index: 930

Text #3

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.6368. Min Act: -0.0000

Data Index: 1143361 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.7931. Min Act: -0.0000

Data Index: 732057 (The Pile)

Max Activating Token Index: 715

Text #5

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.4968. Min Act: -0.0000

Data Index: 1036424 (The Pile)

Max Activating Token Index: 763

Text #6

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.5250. Min Act: -0.0000

Data Index: 1242380 (The Pile)

Max Activating Token Index: 511

Text #7

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.5382. Min Act: -0.0000

Data Index: 73833 (The Pile)

Max Activating Token Index: 684

Text #8

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.5177. Min Act: -0.0000

Data Index: 1063049 (The Pile)

Max Activating Token Index: 404

Text #9

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.6107. Min Act: -0.0000

Data Index: 180915 (The Pile)

Max Activating Token Index: 553

Text #10

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.5304. Min Act: -0.0000

Data Index: 750477 (The Pile)

Max Activating Token Index: 460

Text #11

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.4709. Min Act: -0.0000

Data Index: 257237 (The Pile)

Max Activating Token Index: 413

Text #12

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.4270. Min Act: -0.0000

Data Index: 1018797 (The Pile)

Max Activating Token Index: 509

Text #13

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.4936. Min Act: -0.0000

Data Index: 1451053 (The Pile)

Max Activating Token Index: 42

Text #14

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.3591. Min Act: -0.0000

Data Index: 627168 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.5731. Min Act: -0.0000

Data Index: 954229 (The Pile)

Max Activating Token Index: 658

Text #16

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.5695. Min Act: -0.0000

Data Index: 98225 (The Pile)

Max Activating Token Index: 892

Text #17

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.4967. Min Act: -0.0000

Data Index: 1635238 (The Pile)

Max Activating Token Index: 631

Text #18

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.4514. Min Act: -0.0000

Data Index: 1627773 (The Pile)

Max Activating Token Index: 835

Text #19

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.5287. Min Act: -0.0000

Data Index: 1542724 (The Pile)

Max Activating Token Index: 747