Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2800 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.3865. Min Act: -0.0000

Data Index: 466300 (The Pile)

Max Activating Token Index: 246

Text #1

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.1010. Min Act: -0.0000

Data Index: 1627169 (The Pile)

Max Activating Token Index: 607

Text #2

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.0762. Min Act: -0.0000

Data Index: 1442224 (The Pile)

Max Activating Token Index: 896

Text #3

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.8403. Min Act: -0.0000

Data Index: 187167 (The Pile)

Max Activating Token Index: 673

Text #4

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.0196. Min Act: -0.0000

Data Index: 588229 (The Pile)

Max Activating Token Index: 657

Text #5

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.9491. Min Act: -0.0000

Data Index: 1888417 (The Pile)

Max Activating Token Index: 951

Text #6

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1817520 (The Pile)

Max Activating Token Index: 514

Text #7

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.9641. Min Act: -0.0000

Data Index: 169952 (The Pile)

Max Activating Token Index: 220

Text #8

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.9437. Min Act: -0.0000

Data Index: 1457869 (The Pile)

Max Activating Token Index: 429

Text #9

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1539176 (The Pile)

Max Activating Token Index: 268

Text #10

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.9806. Min Act: -0.0000

Data Index: 1392522 (The Pile)

Max Activating Token Index: 700

Text #11

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1147763 (The Pile)

Max Activating Token Index: 983

Text #12

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.9202. Min Act: -0.0000

Data Index: 567854 (The Pile)

Max Activating Token Index: 632

Text #13

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.8731. Min Act: -0.0000

Data Index: 1138115 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.9475. Min Act: -0.0000

Data Index: 405356 (The Pile)

Max Activating Token Index: 650

Text #15

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.8375. Min Act: -0.0000

Data Index: 1195613 (The Pile)

Max Activating Token Index: 492

Text #16

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.8466. Min Act: -0.0000

Data Index: 1091982 (The Pile)

Max Activating Token Index: 972

Text #17

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1963605 (The Pile)

Max Activating Token Index: 991

Text #18

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1862554 (The Pile)

Max Activating Token Index: 451

Text #19

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.8466. Min Act: -0.0000

Data Index: 478744 (The Pile)

Max Activating Token Index: 837