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

Dataset: The Pile

Neuron 1150 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.6682. Min Act: -0.0000

Data Index: 1228775 (The Pile)

Max Activating Token Index: 968

Text #1

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.5533. Min Act: -0.0000

Data Index: 1180672 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.5172. Min Act: -0.0000

Data Index: 1575442 (The Pile)

Max Activating Token Index: 170

Text #3

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.4989. Min Act: -0.0000

Data Index: 568286 (The Pile)

Max Activating Token Index: 324

Text #4

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.5731. Min Act: -0.0000

Data Index: 1273858 (The Pile)

Max Activating Token Index: 292

Text #5

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.4769. Min Act: -0.0000

Data Index: 1938718 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.4788. Min Act: -0.0000

Data Index: 1368251 (The Pile)

Max Activating Token Index: 731

Text #7

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.4686. Min Act: -0.0000

Data Index: 1982919 (The Pile)

Max Activating Token Index: 664

Text #8

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.3894. Min Act: -0.0000

Data Index: 1712705 (The Pile)

Max Activating Token Index: 618

Text #9

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.4524. Min Act: -0.0000

Data Index: 1364309 (The Pile)

Max Activating Token Index: 97

Text #10

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.3723. Min Act: -0.0000

Data Index: 1330856 (The Pile)

Max Activating Token Index: 891

Text #11

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.4535. Min Act: -0.0000

Data Index: 1856893 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.4364. Min Act: -0.0000

Data Index: 314125 (The Pile)

Max Activating Token Index: 576

Text #13

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.3631. Min Act: -0.0000

Data Index: 860166 (The Pile)

Max Activating Token Index: 1007

Text #14

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.3492. Min Act: -0.0000

Data Index: 755372 (The Pile)

Max Activating Token Index: 458

Text #15

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.4250. Min Act: -0.0000

Data Index: 906693 (The Pile)

Max Activating Token Index: 475

Text #16

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1965097 (The Pile)

Max Activating Token Index: 31

Text #17

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.4030. Min Act: -0.0000

Data Index: 1155873 (The Pile)

Max Activating Token Index: 128

Text #18

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.3943. Min Act: -0.0000

Data Index: 204287 (The Pile)

Max Activating Token Index: 412

Text #19

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.3809. Min Act: -0.0000

Data Index: 1031751 (The Pile)

Max Activating Token Index: 23