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

Dataset: The Pile

Neuron 60 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.0647. Min Act: -0.0000

Data Index: 813861 (The Pile)

Max Activating Token Index: 798

Text #1

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.0348. Min Act: -0.0000

Data Index: 1525629 (The Pile)

Max Activating Token Index: 389

Text #2

Max Range: 3.2372. Min Range: -3.2372

Max Act: 3.2372. Min Act: -0.0000

Data Index: 1916900 (The Pile)

Max Activating Token Index: 50

Text #3

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.4062. Min Act: -0.0000

Data Index: 759920 (The Pile)

Max Activating Token Index: 632

Text #4

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.5824. Min Act: -0.0000

Data Index: 840599 (The Pile)

Max Activating Token Index: 925

Text #5

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.3966. Min Act: -0.0000

Data Index: 984123 (The Pile)

Max Activating Token Index: 977

Text #6

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.3389. Min Act: -0.0000

Data Index: 823202 (The Pile)

Max Activating Token Index: 838

Text #7

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.4152. Min Act: -0.0000

Data Index: 1107548 (The Pile)

Max Activating Token Index: 401

Text #8

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.2115. Min Act: -0.0000

Data Index: 1801326 (The Pile)

Max Activating Token Index: 306

Text #9

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.1091. Min Act: -0.0000

Data Index: 1107013 (The Pile)

Max Activating Token Index: 728

Text #10

Max Range: 3.2372. Min Range: -3.2372

Max Act: 1.9968. Min Act: -0.0000

Data Index: 772659 (The Pile)

Max Activating Token Index: 703

Text #11

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.2446. Min Act: -0.0000

Data Index: 823635 (The Pile)

Max Activating Token Index: 547

Text #12

Max Range: 3.2372. Min Range: -3.2372

Max Act: 1.8677. Min Act: -0.0000

Data Index: 834681 (The Pile)

Max Activating Token Index: 675

Text #13

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.2555. Min Act: -0.0000

Data Index: 691677 (The Pile)

Max Activating Token Index: 267

Text #14

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.0195. Min Act: -0.0000

Data Index: 1753977 (The Pile)

Max Activating Token Index: 868

Text #15

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.0935. Min Act: -0.0000

Data Index: 520477 (The Pile)

Max Activating Token Index: 131

Text #16

Max Range: 3.2372. Min Range: -3.2372

Max Act: 1.8122. Min Act: -0.0000

Data Index: 1640000 (The Pile)

Max Activating Token Index: 676

Text #17

Max Range: 3.2372. Min Range: -3.2372

Max Act: 1.9343. Min Act: -0.0000

Data Index: 1807181 (The Pile)

Max Activating Token Index: 815

Text #18

Max Range: 3.2372. Min Range: -3.2372

Max Act: 1.9094. Min Act: -0.0000

Data Index: 1844103 (The Pile)

Max Activating Token Index: 548

Text #19

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.0064. Min Act: -0.0000

Data Index: 1398490 (The Pile)

Max Activating Token Index: 657