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

Dataset: The Pile

Neuron 2071 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: 1.4950. Min Range: -1.4950

Max Act: 1.1681. Min Act: -0.0000

Data Index: 742566 (The Pile)

Max Activating Token Index: 254

Text #1

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.4041. Min Act: -0.0000

Data Index: 1989991 (The Pile)

Max Activating Token Index: 757

Text #2

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.3481. Min Act: -0.0000

Data Index: 165777 (The Pile)

Max Activating Token Index: 24

Text #3

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.1169. Min Act: -0.0000

Data Index: 285330 (The Pile)

Max Activating Token Index: 789

Text #4

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.4470. Min Act: -0.0000

Data Index: 1790635 (The Pile)

Max Activating Token Index: 919

Text #5

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.4178. Min Act: -0.0000

Data Index: 395485 (The Pile)

Max Activating Token Index: 749

Text #6

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.4950. Min Act: -0.0000

Data Index: 544387 (The Pile)

Max Activating Token Index: 1005

Text #7

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.3025. Min Act: -0.0000

Data Index: 385473 (The Pile)

Max Activating Token Index: 519

Text #8

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.2791. Min Act: -0.0000

Data Index: 938279 (The Pile)

Max Activating Token Index: 459

Text #9

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.2798. Min Act: -0.0000

Data Index: 79724 (The Pile)

Max Activating Token Index: 13

Text #10

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.3555. Min Act: -0.0000

Data Index: 456365 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 1.4950. Min Range: -1.4950

Max Act: 0.9533. Min Act: -0.0000

Data Index: 1611042 (The Pile)

Max Activating Token Index: 787

Text #12

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.2166. Min Act: -0.0000

Data Index: 1555941 (The Pile)

Max Activating Token Index: 812

Text #13

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.1548. Min Act: -0.0000

Data Index: 691587 (The Pile)

Max Activating Token Index: 3

Text #14

Max Range: 1.4950. Min Range: -1.4950

Max Act: 0.9755. Min Act: -0.0000

Data Index: 1571057 (The Pile)

Max Activating Token Index: 743

Text #15

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.2738. Min Act: -0.0000

Data Index: 1567554 (The Pile)

Max Activating Token Index: 457

Text #16

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.1301. Min Act: -0.0000

Data Index: 1805334 (The Pile)

Max Activating Token Index: 938

Text #17

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.0978. Min Act: -0.0000

Data Index: 1957146 (The Pile)

Max Activating Token Index: 943

Text #18

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.0535. Min Act: -0.0000

Data Index: 948122 (The Pile)

Max Activating Token Index: 638

Text #19

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.1726. Min Act: -0.0000

Data Index: 828111 (The Pile)

Max Activating Token Index: 655