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

Dataset: The Pile

Neuron 1640 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4339. Min Range: -3.4339

Max Act: 3.4339. Min Act: -0.0000

Data Index: 414836 (The Pile)

Max Activating Token Index: 239

Text #1

Max Range: 3.4339. Min Range: -3.4339

Max Act: 2.2153. Min Act: -0.0000

Data Index: 609602 (The Pile)

Max Activating Token Index: 396

Text #2

Max Range: 3.4339. Min Range: -3.4339

Max Act: 2.4372. Min Act: -0.0000

Data Index: 1743657 (The Pile)

Max Activating Token Index: 641

Text #3

Max Range: 3.4339. Min Range: -3.4339

Max Act: 2.4065. Min Act: -0.0000

Data Index: 1076679 (The Pile)

Max Activating Token Index: 221

Text #4

Max Range: 3.4339. Min Range: -3.4339

Max Act: 2.2833. Min Act: -0.0000

Data Index: 25063 (The Pile)

Max Activating Token Index: 488

Text #5

Max Range: 3.4339. Min Range: -3.4339

Max Act: 2.0602. Min Act: -0.0000

Data Index: 1135077 (The Pile)

Max Activating Token Index: 141

Text #6

Max Range: 3.4339. Min Range: -3.4339

Max Act: 2.2477. Min Act: -0.0000

Data Index: 1437037 (The Pile)

Max Activating Token Index: 879

Text #7

Max Range: 3.4339. Min Range: -3.4339

Max Act: 2.3385. Min Act: -0.0000

Data Index: 593061 (The Pile)

Max Activating Token Index: 506

Text #8

Max Range: 3.4339. Min Range: -3.4339

Max Act: 2.1836. Min Act: -0.0000

Data Index: 1515800 (The Pile)

Max Activating Token Index: 51

Text #9

Max Range: 3.4339. Min Range: -3.4339

Max Act: 1.7444. Min Act: -0.0000

Data Index: 1209753 (The Pile)

Max Activating Token Index: 140

Text #10

Max Range: 3.4339. Min Range: -3.4339

Max Act: 1.9865. Min Act: -0.0000

Data Index: 1698912 (The Pile)

Max Activating Token Index: 107

Text #11

Max Range: 3.4339. Min Range: -3.4339

Max Act: 1.9411. Min Act: -0.0000

Data Index: 907857 (The Pile)

Max Activating Token Index: 105

Text #12

Max Range: 3.4339. Min Range: -3.4339

Max Act: 1.9253. Min Act: -0.0000

Data Index: 679501 (The Pile)

Max Activating Token Index: 334

Text #13

Max Range: 3.4339. Min Range: -3.4339

Max Act: 1.6608. Min Act: -0.0000

Data Index: 853264 (The Pile)

Max Activating Token Index: 767

Text #14

Max Range: 3.4339. Min Range: -3.4339

Max Act: 1.7900. Min Act: -0.0000

Data Index: 250894 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 3.4339. Min Range: -3.4339

Max Act: 2.0044. Min Act: -0.0000

Data Index: 1066299 (The Pile)

Max Activating Token Index: 230

Text #16

Max Range: 3.4339. Min Range: -3.4339

Max Act: 1.5773. Min Act: -0.0000

Data Index: 984542 (The Pile)

Max Activating Token Index: 687

Text #17

Max Range: 3.4339. Min Range: -3.4339

Max Act: 1.7097. Min Act: -0.0000

Data Index: 883744 (The Pile)

Max Activating Token Index: 941

Text #18

Max Range: 3.4339. Min Range: -3.4339

Max Act: 1.4971. Min Act: -0.0000

Data Index: 951008 (The Pile)

Max Activating Token Index: 35

Text #19

Max Range: 3.4339. Min Range: -3.4339

Max Act: 1.6057. Min Act: -0.0000

Data Index: 826570 (The Pile)

Max Activating Token Index: 209