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

Dataset: The Pile

Neuron 3751 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: 0.0727. Min Range: -0.0727

Max Act: 0.0580. Min Act: -0.0000

Data Index: 44761 (The Pile)

Max Activating Token Index: 988

Text #1

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0727. Min Act: -0.0000

Data Index: 595694 (The Pile)

Max Activating Token Index: 389

Text #2

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0664. Min Act: -0.0000

Data Index: 197291 (The Pile)

Max Activating Token Index: 143

Text #3

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0570. Min Act: -0.0000

Data Index: 1363888 (The Pile)

Max Activating Token Index: 91

Text #4

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0606. Min Act: -0.0000

Data Index: 1262452 (The Pile)

Max Activating Token Index: 400

Text #5

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0622. Min Act: -0.0000

Data Index: 141953 (The Pile)

Max Activating Token Index: 376

Text #6

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0510. Min Act: -0.0000

Data Index: 1130532 (The Pile)

Max Activating Token Index: 583

Text #7

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0480. Min Act: -0.0000

Data Index: 408555 (The Pile)

Max Activating Token Index: 724

Text #8

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0478. Min Act: -0.0000

Data Index: 1725924 (The Pile)

Max Activating Token Index: 189

Text #9

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0571. Min Act: -0.0000

Data Index: 828256 (The Pile)

Max Activating Token Index: 640

Text #10

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0457. Min Act: -0.0000

Data Index: 1470694 (The Pile)

Max Activating Token Index: 448

Text #11

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0492. Min Act: -0.0000

Data Index: 1183383 (The Pile)

Max Activating Token Index: 193

Text #12

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0475. Min Act: -0.0000

Data Index: 1005387 (The Pile)

Max Activating Token Index: 982

Text #13

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0489. Min Act: -0.0000

Data Index: 1732833 (The Pile)

Max Activating Token Index: 230

Text #14

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0445. Min Act: -0.0000

Data Index: 1940787 (The Pile)

Max Activating Token Index: 210

Text #15

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0449. Min Act: -0.0000

Data Index: 339811 (The Pile)

Max Activating Token Index: 637

Text #16

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0462. Min Act: -0.0000

Data Index: 1153514 (The Pile)

Max Activating Token Index: 1006

Text #17

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0472. Min Act: -0.0000

Data Index: 744208 (The Pile)

Max Activating Token Index: 570

Text #18

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0436. Min Act: -0.0000

Data Index: 140651 (The Pile)

Max Activating Token Index: 118

Text #19

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0454. Min Act: -0.0000

Data Index: 1009351 (The Pile)

Max Activating Token Index: 681