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

Dataset: The Pile

Neuron 4138 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0511. Min Range: -1.0511

Max Act: 1.0511. Min Act: -0.0000

Data Index: 23335 (The Pile)

Max Activating Token Index: 689

Text #1

Max Range: 1.0511. Min Range: -1.0511

Max Act: 1.0413. Min Act: -0.0000

Data Index: 401063 (The Pile)

Max Activating Token Index: 566

Text #2

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9933. Min Act: -0.0000

Data Index: 88465 (The Pile)

Max Activating Token Index: 756

Text #3

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9932. Min Act: -0.0000

Data Index: 726742 (The Pile)

Max Activating Token Index: 451

Text #4

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6807. Min Act: -0.0000

Data Index: 907452 (The Pile)

Max Activating Token Index: 274

Text #5

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6598. Min Act: -0.0000

Data Index: 730367 (The Pile)

Max Activating Token Index: 541

Text #6

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6865. Min Act: -0.0000

Data Index: 720193 (The Pile)

Max Activating Token Index: 67

Text #7

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1418860 (The Pile)

Max Activating Token Index: 221

Text #8

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1625274 (The Pile)

Max Activating Token Index: 552

Text #9

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1071532 (The Pile)

Max Activating Token Index: 68

Text #10

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1632656 (The Pile)

Max Activating Token Index: 255

Text #11

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1034914 (The Pile)

Max Activating Token Index: 998

Text #12

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1592213 (The Pile)

Max Activating Token Index: 302

Text #13

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6505. Min Act: -0.0000

Data Index: 787608 (The Pile)

Max Activating Token Index: 555

Text #14

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1989991 (The Pile)

Max Activating Token Index: 753

Text #15

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1914646 (The Pile)

Max Activating Token Index: 766

Text #16

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6232. Min Act: -0.0000

Data Index: 983635 (The Pile)

Max Activating Token Index: 123

Text #17

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1998740 (The Pile)

Max Activating Token Index: 975

Text #18

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1185967 (The Pile)

Max Activating Token Index: 1008

Text #19

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1371802 (The Pile)

Max Activating Token Index: 873