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

Dataset: The Pile

Neuron 2518 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: 1.2098. Min Range: -1.2098

Max Act: 1.1122. Min Act: -0.0000

Data Index: 1789195 (The Pile)

Max Activating Token Index: 261

Text #1

Max Range: 1.2098. Min Range: -1.2098

Max Act: 1.1838. Min Act: -0.0000

Data Index: 808834 (The Pile)

Max Activating Token Index: 381

Text #2

Max Range: 1.2098. Min Range: -1.2098

Max Act: 1.1579. Min Act: -0.0000

Data Index: 530852 (The Pile)

Max Activating Token Index: 230

Text #3

Max Range: 1.2098. Min Range: -1.2098

Max Act: 1.1370. Min Act: -0.0000

Data Index: 1717508 (The Pile)

Max Activating Token Index: 474

Text #4

Max Range: 1.2098. Min Range: -1.2098

Max Act: 1.2098. Min Act: -0.0000

Data Index: 1787085 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 1.2098. Min Range: -1.2098

Max Act: 1.0450. Min Act: -0.0000

Data Index: 1489525 (The Pile)

Max Activating Token Index: 481

Text #6

Max Range: 1.2098. Min Range: -1.2098

Max Act: 1.0072. Min Act: -0.0000

Data Index: 955017 (The Pile)

Max Activating Token Index: 174

Text #7

Max Range: 1.2098. Min Range: -1.2098

Max Act: 1.0814. Min Act: -0.0000

Data Index: 1748201 (The Pile)

Max Activating Token Index: 140

Text #8

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.9620. Min Act: -0.0000

Data Index: 974062 (The Pile)

Max Activating Token Index: 498

Text #9

Max Range: 1.2098. Min Range: -1.2098

Max Act: 1.0007. Min Act: -0.0000

Data Index: 518586 (The Pile)

Max Activating Token Index: 265

Text #10

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.8433. Min Act: -0.0000

Data Index: 1795446 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.9465. Min Act: -0.0000

Data Index: 1274834 (The Pile)

Max Activating Token Index: 796

Text #12

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.9383. Min Act: -0.0000

Data Index: 1338057 (The Pile)

Max Activating Token Index: 721

Text #13

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.9554. Min Act: -0.0000

Data Index: 1843837 (The Pile)

Max Activating Token Index: 169

Text #14

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.9022. Min Act: -0.0000

Data Index: 1191584 (The Pile)

Max Activating Token Index: 155

Text #15

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.9843. Min Act: -0.0000

Data Index: 1825516 (The Pile)

Max Activating Token Index: 148

Text #16

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.8956. Min Act: -0.0000

Data Index: 346320 (The Pile)

Max Activating Token Index: 384

Text #17

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.9114. Min Act: -0.0000

Data Index: 42298 (The Pile)

Max Activating Token Index: 621

Text #18

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1517996 (The Pile)

Max Activating Token Index: 753

Text #19

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1045106 (The Pile)

Max Activating Token Index: 748