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

Dataset: The Pile

Neuron 1953 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: 4.7571. Min Range: -4.7571

Max Act: 4.7571. Min Act: -0.0000

Data Index: 412295 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.5066. Min Act: -0.0000

Data Index: 607701 (The Pile)

Max Activating Token Index: 385

Text #2

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.3437. Min Act: -0.0000

Data Index: 474703 (The Pile)

Max Activating Token Index: 7

Text #3

Max Range: 4.7571. Min Range: -4.7571

Max Act: 3.8066. Min Act: -0.0000

Data Index: 332692 (The Pile)

Max Activating Token Index: 757

Text #4

Max Range: 4.7571. Min Range: -4.7571

Max Act: 3.7318. Min Act: -0.0000

Data Index: 128503 (The Pile)

Max Activating Token Index: 422

Text #5

Max Range: 4.7571. Min Range: -4.7571

Max Act: 3.8934. Min Act: -0.0000

Data Index: 794161 (The Pile)

Max Activating Token Index: 527

Text #6

Max Range: 4.7571. Min Range: -4.7571

Max Act: 3.7262. Min Act: -0.0000

Data Index: 977320 (The Pile)

Max Activating Token Index: 638

Text #7

Max Range: 4.7571. Min Range: -4.7571

Max Act: 3.8179. Min Act: -0.0000

Data Index: 200178 (The Pile)

Max Activating Token Index: 18

Text #8

Max Range: 4.7571. Min Range: -4.7571

Max Act: 3.8053. Min Act: -0.0000

Data Index: 766973 (The Pile)

Max Activating Token Index: 561

Text #9

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.1023. Min Act: -0.0000

Data Index: 1283334 (The Pile)

Max Activating Token Index: 671

Text #10

Max Range: 4.7571. Min Range: -4.7571

Max Act: 3.6235. Min Act: -0.0000

Data Index: 1697517 (The Pile)

Max Activating Token Index: 763

Text #11

Max Range: 4.7571. Min Range: -4.7571

Max Act: 3.7696. Min Act: -0.0000

Data Index: 946443 (The Pile)

Max Activating Token Index: 146

Text #12

Max Range: 4.7571. Min Range: -4.7571

Max Act: 3.5866. Min Act: -0.0000

Data Index: 1758369 (The Pile)

Max Activating Token Index: 313

Text #13

Max Range: 4.7571. Min Range: -4.7571

Max Act: 3.7196. Min Act: -0.0000

Data Index: 14342 (The Pile)

Max Activating Token Index: 483

Text #14

Max Range: 4.7571. Min Range: -4.7571

Max Act: 3.8878. Min Act: -0.0000

Data Index: 735656 (The Pile)

Max Activating Token Index: 1002

Text #15

Max Range: 4.7571. Min Range: -4.7571

Max Act: 3.5270. Min Act: -0.0000

Data Index: 1115868 (The Pile)

Max Activating Token Index: 191

Text #16

Max Range: 4.7571. Min Range: -4.7571

Max Act: 3.5518. Min Act: -0.0000

Data Index: 1643989 (The Pile)

Max Activating Token Index: 798

Text #17

Max Range: 4.7571. Min Range: -4.7571

Max Act: 3.8291. Min Act: -0.0000

Data Index: 787370 (The Pile)

Max Activating Token Index: 711

Text #18

Max Range: 4.7571. Min Range: -4.7571

Max Act: 3.8346. Min Act: -0.0000

Data Index: 155348 (The Pile)

Max Activating Token Index: 605

Text #19

Max Range: 4.7571. Min Range: -4.7571

Max Act: 3.8286. Min Act: -0.0000

Data Index: 3232 (The Pile)

Max Activating Token Index: 799