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

Dataset: The Pile

Neuron 4007 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: 1.1201. Min Range: -1.1201

Max Act: 1.1169. Min Act: -0.0000

Data Index: 1513032 (The Pile)

Max Activating Token Index: 250

Text #1

Max Range: 1.1201. Min Range: -1.1201

Max Act: 1.1201. Min Act: -0.0000

Data Index: 223088 (The Pile)

Max Activating Token Index: 982

Text #2

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.9775. Min Act: -0.0000

Data Index: 485970 (The Pile)

Max Activating Token Index: 76

Text #3

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.9786. Min Act: -0.0000

Data Index: 221848 (The Pile)

Max Activating Token Index: 200

Text #4

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1925817 (The Pile)

Max Activating Token Index: 964

Text #5

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.9918. Min Act: -0.0000

Data Index: 1732013 (The Pile)

Max Activating Token Index: 536

Text #6

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.9020. Min Act: -0.0000

Data Index: 1936665 (The Pile)

Max Activating Token Index: 864

Text #7

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.8219. Min Act: -0.0000

Data Index: 545766 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.9339. Min Act: -0.0000

Data Index: 508019 (The Pile)

Max Activating Token Index: 686

Text #9

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.9023. Min Act: -0.0000

Data Index: 831056 (The Pile)

Max Activating Token Index: 259

Text #10

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.7797. Min Act: -0.0000

Data Index: 1801144 (The Pile)

Max Activating Token Index: 825

Text #11

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1295741 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.8153. Min Act: -0.0000

Data Index: 1768037 (The Pile)

Max Activating Token Index: 188

Text #13

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.7916. Min Act: -0.0000

Data Index: 1006261 (The Pile)

Max Activating Token Index: 622

Text #14

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.8118. Min Act: -0.0000

Data Index: 788882 (The Pile)

Max Activating Token Index: 924

Text #15

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1914711 (The Pile)

Max Activating Token Index: 425

Text #16

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1110201 (The Pile)

Max Activating Token Index: 637

Text #17

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1845278 (The Pile)

Max Activating Token Index: 788

Text #18

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.7556. Min Act: -0.0000

Data Index: 572835 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 1.1201. Min Range: -1.1201

Max Act: 0.7566. Min Act: -0.0000

Data Index: 1425562 (The Pile)

Max Activating Token Index: 568