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

Dataset: The Pile

Neuron 2879 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8897. Min Range: -1.8897

Max Act: 1.8897. Min Act: -0.0000

Data Index: 1937153 (The Pile)

Max Activating Token Index: 404

Text #1

Max Range: 1.8897. Min Range: -1.8897

Max Act: 1.0828. Min Act: -0.0000

Data Index: 983841 (The Pile)

Max Activating Token Index: 795

Text #2

Max Range: 1.8897. Min Range: -1.8897

Max Act: 1.0277. Min Act: -0.0000

Data Index: 1683828 (The Pile)

Max Activating Token Index: 620

Text #3

Max Range: 1.8897. Min Range: -1.8897

Max Act: 0.9321. Min Act: -0.0000

Data Index: 1522028 (The Pile)

Max Activating Token Index: 287

Text #4

Max Range: 1.8897. Min Range: -1.8897

Max Act: 1.0794. Min Act: -0.0000

Data Index: 1583810 (The Pile)

Max Activating Token Index: 508

Text #5

Max Range: 1.8897. Min Range: -1.8897

Max Act: 0.9624. Min Act: -0.0000

Data Index: 1199435 (The Pile)

Max Activating Token Index: 347

Text #6

Max Range: 1.8897. Min Range: -1.8897

Max Act: 0.9969. Min Act: -0.0000

Data Index: 813001 (The Pile)

Max Activating Token Index: 130

Text #7

Max Range: 1.8897. Min Range: -1.8897

Max Act: 1.0080. Min Act: -0.0000

Data Index: 1242109 (The Pile)

Max Activating Token Index: 517

Text #8

Max Range: 1.8897. Min Range: -1.8897

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1607991 (The Pile)

Max Activating Token Index: 564

Text #9

Max Range: 1.8897. Min Range: -1.8897

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1480476 (The Pile)

Max Activating Token Index: 344

Text #10

Max Range: 1.8897. Min Range: -1.8897

Max Act: 0.8753. Min Act: -0.0000

Data Index: 1974665 (The Pile)

Max Activating Token Index: 943

Text #11

Max Range: 1.8897. Min Range: -1.8897

Max Act: 0.9795. Min Act: -0.0000

Data Index: 396194 (The Pile)

Max Activating Token Index: 652

Text #12

Max Range: 1.8897. Min Range: -1.8897

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1754230 (The Pile)

Max Activating Token Index: 883

Text #13

Max Range: 1.8897. Min Range: -1.8897

Max Act: 0.9490. Min Act: -0.0000

Data Index: 852650 (The Pile)

Max Activating Token Index: 924

Text #14

Max Range: 1.8897. Min Range: -1.8897

Max Act: 0.9638. Min Act: -0.0000

Data Index: 825528 (The Pile)

Max Activating Token Index: 643

Text #15

Max Range: 1.8897. Min Range: -1.8897

Max Act: 0.9365. Min Act: -0.0000

Data Index: 75529 (The Pile)

Max Activating Token Index: 789

Text #16

Max Range: 1.8897. Min Range: -1.8897

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1453039 (The Pile)

Max Activating Token Index: 909

Text #17

Max Range: 1.8897. Min Range: -1.8897

Max Act: 0.8241. Min Act: -0.0000

Data Index: 695188 (The Pile)

Max Activating Token Index: 668

Text #18

Max Range: 1.8897. Min Range: -1.8897

Max Act: 0.9018. Min Act: -0.0000

Data Index: 1679416 (The Pile)

Max Activating Token Index: 143

Text #19

Max Range: 1.8897. Min Range: -1.8897

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1996944 (The Pile)

Max Activating Token Index: 993