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

Dataset: The Pile

Neuron 4787 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: 1.3099. Min Range: -1.3099

Max Act: 1.3099. Min Act: -0.0000

Data Index: 302028 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 1.3099. Min Range: -1.3099

Max Act: 1.2644. Min Act: -0.0000

Data Index: 715152 (The Pile)

Max Activating Token Index: 796

Text #2

Max Range: 1.3099. Min Range: -1.3099

Max Act: 1.2071. Min Act: -0.0000

Data Index: 1718164 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 1.3099. Min Range: -1.3099

Max Act: 1.0671. Min Act: -0.0000

Data Index: 666679 (The Pile)

Max Activating Token Index: 76

Text #4

Max Range: 1.3099. Min Range: -1.3099

Max Act: 1.0546. Min Act: -0.0000

Data Index: 1643011 (The Pile)

Max Activating Token Index: 366

Text #5

Max Range: 1.3099. Min Range: -1.3099

Max Act: 1.1250. Min Act: -0.0000

Data Index: 1806340 (The Pile)

Max Activating Token Index: 612

Text #6

Max Range: 1.3099. Min Range: -1.3099

Max Act: 1.0841. Min Act: -0.0000

Data Index: 27088 (The Pile)

Max Activating Token Index: 257

Text #7

Max Range: 1.3099. Min Range: -1.3099

Max Act: 1.0068. Min Act: -0.0000

Data Index: 1222004 (The Pile)

Max Activating Token Index: 109

Text #8

Max Range: 1.3099. Min Range: -1.3099

Max Act: 1.0725. Min Act: -0.0000

Data Index: 1473068 (The Pile)

Max Activating Token Index: 743

Text #9

Max Range: 1.3099. Min Range: -1.3099

Max Act: 1.1227. Min Act: -0.0000

Data Index: 1788115 (The Pile)

Max Activating Token Index: 813

Text #10

Max Range: 1.3099. Min Range: -1.3099

Max Act: 1.0211. Min Act: -0.0000

Data Index: 347079 (The Pile)

Max Activating Token Index: 394

Text #11

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.9917. Min Act: -0.0000

Data Index: 299789 (The Pile)

Max Activating Token Index: 574

Text #12

Max Range: 1.3099. Min Range: -1.3099

Max Act: 1.0316. Min Act: -0.0000

Data Index: 991397 (The Pile)

Max Activating Token Index: 329

Text #13

Max Range: 1.3099. Min Range: -1.3099

Max Act: 1.0674. Min Act: -0.0000

Data Index: 1786944 (The Pile)

Max Activating Token Index: 315

Text #14

Max Range: 1.3099. Min Range: -1.3099

Max Act: 1.0197. Min Act: -0.0000

Data Index: 589856 (The Pile)

Max Activating Token Index: 416

Text #15

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.9904. Min Act: -0.0000

Data Index: 1592379 (The Pile)

Max Activating Token Index: 227

Text #16

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.9844. Min Act: -0.0000

Data Index: 823102 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 1.3099. Min Range: -1.3099

Max Act: 1.0145. Min Act: -0.0000

Data Index: 1874381 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.8834. Min Act: -0.0000

Data Index: 1662754 (The Pile)

Max Activating Token Index: 663

Text #19

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.9340. Min Act: -0.0000

Data Index: 106296 (The Pile)

Max Activating Token Index: 16