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

Dataset: The Pile

Neuron 2997 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: 1.0788. Min Range: -1.0788

Max Act: 1.0788. Min Act: -0.0000

Data Index: 936462 (The Pile)

Max Activating Token Index: 644

Text #1

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.9419. Min Act: -0.0000

Data Index: 1821402 (The Pile)

Max Activating Token Index: 990

Text #2

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.9094. Min Act: -0.0000

Data Index: 1334177 (The Pile)

Max Activating Token Index: 125

Text #3

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8620. Min Act: -0.0000

Data Index: 1373160 (The Pile)

Max Activating Token Index: 523

Text #4

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8711. Min Act: -0.0000

Data Index: 1853335 (The Pile)

Max Activating Token Index: 141

Text #5

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.7869. Min Act: -0.0000

Data Index: 152503 (The Pile)

Max Activating Token Index: 622

Text #6

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1618917 (The Pile)

Max Activating Token Index: 808

Text #7

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.7700. Min Act: -0.0000

Data Index: 1627281 (The Pile)

Max Activating Token Index: 834

Text #8

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8194. Min Act: -0.0000

Data Index: 815161 (The Pile)

Max Activating Token Index: 365

Text #9

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8206. Min Act: -0.0000

Data Index: 1994047 (The Pile)

Max Activating Token Index: 531

Text #10

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8189. Min Act: -0.0000

Data Index: 702449 (The Pile)

Max Activating Token Index: 536

Text #11

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8163. Min Act: -0.0000

Data Index: 1317996 (The Pile)

Max Activating Token Index: 127

Text #12

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1084973 (The Pile)

Max Activating Token Index: 115

Text #13

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.7786. Min Act: -0.0000

Data Index: 130029 (The Pile)

Max Activating Token Index: 131

Text #14

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.7510. Min Act: -0.0000

Data Index: 1059559 (The Pile)

Max Activating Token Index: 500

Text #15

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1482792 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8141. Min Act: -0.0000

Data Index: 700339 (The Pile)

Max Activating Token Index: 615

Text #17

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.7582. Min Act: -0.0000

Data Index: 327584 (The Pile)

Max Activating Token Index: 202

Text #18

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1923199 (The Pile)

Max Activating Token Index: 934

Text #19

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1666730 (The Pile)

Max Activating Token Index: 394