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

Dataset: The Pile

Neuron 899 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: 3.0962. Min Range: -3.0962

Max Act: 3.0962. Min Act: -0.0000

Data Index: 843837 (The Pile)

Max Activating Token Index: 428

Text #1

Max Range: 3.0962. Min Range: -3.0962

Max Act: 2.2518. Min Act: -0.0000

Data Index: 635772 (The Pile)

Max Activating Token Index: 236

Text #2

Max Range: 3.0962. Min Range: -3.0962

Max Act: 2.0534. Min Act: -0.0000

Data Index: 1658511 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 3.0962. Min Range: -3.0962

Max Act: 2.1533. Min Act: -0.0000

Data Index: 941429 (The Pile)

Max Activating Token Index: 100

Text #4

Max Range: 3.0962. Min Range: -3.0962

Max Act: 2.1653. Min Act: -0.0000

Data Index: 325973 (The Pile)

Max Activating Token Index: 185

Text #5

Max Range: 3.0962. Min Range: -3.0962

Max Act: 2.1432. Min Act: -0.0000

Data Index: 27443 (The Pile)

Max Activating Token Index: 349

Text #6

Max Range: 3.0962. Min Range: -3.0962

Max Act: 2.1600. Min Act: -0.0000

Data Index: 373387 (The Pile)

Max Activating Token Index: 101

Text #7

Max Range: 3.0962. Min Range: -3.0962

Max Act: 2.0234. Min Act: -0.0000

Data Index: 83295 (The Pile)

Max Activating Token Index: 756

Text #8

Max Range: 3.0962. Min Range: -3.0962

Max Act: 2.1337. Min Act: -0.0000

Data Index: 749402 (The Pile)

Max Activating Token Index: 329

Text #9

Max Range: 3.0962. Min Range: -3.0962

Max Act: 1.8333. Min Act: -0.0000

Data Index: 733722 (The Pile)

Max Activating Token Index: 987

Text #10

Max Range: 3.0962. Min Range: -3.0962

Max Act: 1.9835. Min Act: -0.0000

Data Index: 1214192 (The Pile)

Max Activating Token Index: 560

Text #11

Max Range: 3.0962. Min Range: -3.0962

Max Act: 1.9570. Min Act: -0.0000

Data Index: 1571383 (The Pile)

Max Activating Token Index: 198

Text #12

Max Range: 3.0962. Min Range: -3.0962

Max Act: 1.8465. Min Act: -0.0000

Data Index: 183899 (The Pile)

Max Activating Token Index: 104

Text #13

Max Range: 3.0962. Min Range: -3.0962

Max Act: 1.6469. Min Act: -0.0000

Data Index: 784420 (The Pile)

Max Activating Token Index: 228

Text #14

Max Range: 3.0962. Min Range: -3.0962

Max Act: 1.9461. Min Act: -0.0000

Data Index: 1597961 (The Pile)

Max Activating Token Index: 59

Text #15

Max Range: 3.0962. Min Range: -3.0962

Max Act: 1.7373. Min Act: -0.0000

Data Index: 56663 (The Pile)

Max Activating Token Index: 931

Text #16

Max Range: 3.0962. Min Range: -3.0962

Max Act: 1.9625. Min Act: -0.0000

Data Index: 1284770 (The Pile)

Max Activating Token Index: 587

Text #17

Max Range: 3.0962. Min Range: -3.0962

Max Act: 1.7359. Min Act: -0.0000

Data Index: 144991 (The Pile)

Max Activating Token Index: 113

Text #18

Max Range: 3.0962. Min Range: -3.0962

Max Act: 1.8486. Min Act: -0.0000

Data Index: 1225705 (The Pile)

Max Activating Token Index: 285

Text #19

Max Range: 3.0962. Min Range: -3.0962

Max Act: 1.8157. Min Act: -0.0000

Data Index: 847213 (The Pile)

Max Activating Token Index: 198