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

Dataset: The Pile

Neuron 3623 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: 0.3157. Min Range: -0.3157

Max Act: 0.2889. Min Act: -0.0000

Data Index: 398577 (The Pile)

Max Activating Token Index: 708

Text #1

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.3157. Min Act: -0.0000

Data Index: 204863 (The Pile)

Max Activating Token Index: 737

Text #2

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1431363 (The Pile)

Max Activating Token Index: 295

Text #3

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1328533 (The Pile)

Max Activating Token Index: 999

Text #4

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2928. Min Act: -0.0000

Data Index: 203351 (The Pile)

Max Activating Token Index: 810

Text #5

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1080071 (The Pile)

Max Activating Token Index: 820

Text #6

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2709. Min Act: -0.0000

Data Index: 1413572 (The Pile)

Max Activating Token Index: 772

Text #7

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1158696 (The Pile)

Max Activating Token Index: 903

Text #8

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2888. Min Act: -0.0000

Data Index: 465157 (The Pile)

Max Activating Token Index: 372

Text #9

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1302655 (The Pile)

Max Activating Token Index: 838

Text #10

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2653. Min Act: -0.0000

Data Index: 564801 (The Pile)

Max Activating Token Index: 986

Text #11

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1489155 (The Pile)

Max Activating Token Index: 131

Text #12

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2646. Min Act: -0.0000

Data Index: 712772 (The Pile)

Max Activating Token Index: 518

Text #13

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2612. Min Act: -0.0000

Data Index: 992873 (The Pile)

Max Activating Token Index: 565

Text #14

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1288612 (The Pile)

Max Activating Token Index: 118

Text #15

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1978695 (The Pile)

Max Activating Token Index: 320

Text #16

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1317657 (The Pile)

Max Activating Token Index: 940

Text #17

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2452. Min Act: -0.0000

Data Index: 1469998 (The Pile)

Max Activating Token Index: 562

Text #18

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1771948 (The Pile)

Max Activating Token Index: 308

Text #19

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2425. Min Act: -0.0000

Data Index: 914771 (The Pile)

Max Activating Token Index: 375