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

Dataset: The Pile

Neuron 3280 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.3162. Min Act: -0.0000

Data Index: 382415 (The Pile)

Max Activating Token Index: 503

Text #1

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2701. Min Act: -0.0000

Data Index: 309518 (The Pile)

Max Activating Token Index: 86

Text #2

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2571. Min Act: -0.0000

Data Index: 249015 (The Pile)

Max Activating Token Index: 310

Text #3

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2828. Min Act: -0.0000

Data Index: 369859 (The Pile)

Max Activating Token Index: 892

Text #4

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2581. Min Act: -0.0000

Data Index: 252619 (The Pile)

Max Activating Token Index: 887

Text #5

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2505. Min Act: -0.0000

Data Index: 971956 (The Pile)

Max Activating Token Index: 666

Text #6

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1287685 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1154118 (The Pile)

Max Activating Token Index: 604

Text #8

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1240855 (The Pile)

Max Activating Token Index: 491

Text #9

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2316. Min Act: -0.0000

Data Index: 1564022 (The Pile)

Max Activating Token Index: 86

Text #10

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2283. Min Act: -0.0000

Data Index: 1505794 (The Pile)

Max Activating Token Index: 1022

Text #11

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1496447 (The Pile)

Max Activating Token Index: 296

Text #12

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1172103 (The Pile)

Max Activating Token Index: 240

Text #13

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1487984 (The Pile)

Max Activating Token Index: 176

Text #14

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2286. Min Act: -0.0000

Data Index: 375951 (The Pile)

Max Activating Token Index: 84

Text #15

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1615060 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2207. Min Act: -0.0000

Data Index: 1699284 (The Pile)

Max Activating Token Index: 103

Text #17

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2158. Min Act: -0.0000

Data Index: 1755306 (The Pile)

Max Activating Token Index: 950

Text #18

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2189. Min Act: -0.0000

Data Index: 713352 (The Pile)

Max Activating Token Index: 780

Text #19

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2075. Min Act: -0.0000

Data Index: 201829 (The Pile)

Max Activating Token Index: 533