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

Dataset: The Pile

Neuron 4318 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: 3.5453. Min Range: -3.5453

Max Act: 3.5453. Min Act: -0.0000

Data Index: 344147 (The Pile)

Max Activating Token Index: 882

Text #1

Max Range: 3.5453. Min Range: -3.5453

Max Act: 3.2905. Min Act: -0.0000

Data Index: 271588 (The Pile)

Max Activating Token Index: 301

Text #2

Max Range: 3.5453. Min Range: -3.5453

Max Act: 3.2933. Min Act: -0.0000

Data Index: 1087838 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 3.5453. Min Range: -3.5453

Max Act: 3.1537. Min Act: -0.0000

Data Index: 1346354 (The Pile)

Max Activating Token Index: 696

Text #4

Max Range: 3.5453. Min Range: -3.5453

Max Act: 3.1052. Min Act: -0.0000

Data Index: 1631071 (The Pile)

Max Activating Token Index: 180

Text #5

Max Range: 3.5453. Min Range: -3.5453

Max Act: 2.9182. Min Act: -0.0000

Data Index: 452196 (The Pile)

Max Activating Token Index: 521

Text #6

Max Range: 3.5453. Min Range: -3.5453

Max Act: 2.8047. Min Act: -0.0000

Data Index: 1992931 (The Pile)

Max Activating Token Index: 78

Text #7

Max Range: 3.5453. Min Range: -3.5453

Max Act: 2.8438. Min Act: -0.0000

Data Index: 1115074 (The Pile)

Max Activating Token Index: 164

Text #8

Max Range: 3.5453. Min Range: -3.5453

Max Act: 2.7162. Min Act: -0.0000

Data Index: 139922 (The Pile)

Max Activating Token Index: 515

Text #9

Max Range: 3.5453. Min Range: -3.5453

Max Act: 2.8134. Min Act: -0.0000

Data Index: 425246 (The Pile)

Max Activating Token Index: 142

Text #10

Max Range: 3.5453. Min Range: -3.5453

Max Act: 2.6610. Min Act: -0.0000

Data Index: 1311176 (The Pile)

Max Activating Token Index: 44

Text #11

Max Range: 3.5453. Min Range: -3.5453

Max Act: 2.7671. Min Act: -0.0000

Data Index: 560325 (The Pile)

Max Activating Token Index: 547

Text #12

Max Range: 3.5453. Min Range: -3.5453

Max Act: 2.7457. Min Act: -0.0000

Data Index: 1028460 (The Pile)

Max Activating Token Index: 849

Text #13

Max Range: 3.5453. Min Range: -3.5453

Max Act: 2.6626. Min Act: -0.0000

Data Index: 1791052 (The Pile)

Max Activating Token Index: 798

Text #14

Max Range: 3.5453. Min Range: -3.5453

Max Act: 2.6802. Min Act: -0.0000

Data Index: 1899876 (The Pile)

Max Activating Token Index: 417

Text #15

Max Range: 3.5453. Min Range: -3.5453

Max Act: 2.5227. Min Act: -0.0000

Data Index: 1873226 (The Pile)

Max Activating Token Index: 207

Text #16

Max Range: 3.5453. Min Range: -3.5453

Max Act: 2.6079. Min Act: -0.0000

Data Index: 1756872 (The Pile)

Max Activating Token Index: 553

Text #17

Max Range: 3.5453. Min Range: -3.5453

Max Act: 2.3532. Min Act: -0.0000

Data Index: 1347037 (The Pile)

Max Activating Token Index: 645

Text #18

Max Range: 3.5453. Min Range: -3.5453

Max Act: 2.6324. Min Act: -0.0000

Data Index: 1152070 (The Pile)

Max Activating Token Index: 522

Text #19

Max Range: 3.5453. Min Range: -3.5453

Max Act: 2.7382. Min Act: -0.0000

Data Index: 1292637 (The Pile)

Max Activating Token Index: 70