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

Dataset: The Pile

Neuron 2449 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.3789. Min Act: -0.0000

Data Index: 67667 (The Pile)

Max Activating Token Index: 70

Text #1

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.2685. Min Act: -0.0000

Data Index: 720803 (The Pile)

Max Activating Token Index: 251

Text #2

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.2215. Min Act: -0.0000

Data Index: 584751 (The Pile)

Max Activating Token Index: 754

Text #3

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.2649. Min Act: -0.0000

Data Index: 940056 (The Pile)

Max Activating Token Index: 570

Text #4

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.2442. Min Act: -0.0000

Data Index: 1245613 (The Pile)

Max Activating Token Index: 591

Text #5

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.1713. Min Act: -0.0000

Data Index: 218437 (The Pile)

Max Activating Token Index: 526

Text #6

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.1283. Min Act: -0.0000

Data Index: 731335 (The Pile)

Max Activating Token Index: 267

Text #7

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.1484. Min Act: -0.0000

Data Index: 579686 (The Pile)

Max Activating Token Index: 42

Text #8

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.1031. Min Act: -0.0000

Data Index: 207569 (The Pile)

Max Activating Token Index: 76

Text #9

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.0696. Min Act: -0.0000

Data Index: 1358383 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.0811. Min Act: -0.0000

Data Index: 1036185 (The Pile)

Max Activating Token Index: 184

Text #11

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.0819. Min Act: -0.0000

Data Index: 1162953 (The Pile)

Max Activating Token Index: 71

Text #12

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.0195. Min Act: -0.0000

Data Index: 1723336 (The Pile)

Max Activating Token Index: 409

Text #13

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.0469. Min Act: -0.0000

Data Index: 1447189 (The Pile)

Max Activating Token Index: 262

Text #14

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.0349. Min Act: -0.0000

Data Index: 1736537 (The Pile)

Max Activating Token Index: 434

Text #15

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.0179. Min Act: -0.0000

Data Index: 1818525 (The Pile)

Max Activating Token Index: 562

Text #16

Max Range: 1.3789. Min Range: -1.3789

Max Act: 0.9595. Min Act: -0.0000

Data Index: 1287140 (The Pile)

Max Activating Token Index: 222

Text #17

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.0154. Min Act: -0.0000

Data Index: 343494 (The Pile)

Max Activating Token Index: 662

Text #18

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.0433. Min Act: -0.0000

Data Index: 326102 (The Pile)

Max Activating Token Index: 178

Text #19

Max Range: 1.3789. Min Range: -1.3789

Max Act: 0.9688. Min Act: -0.0000

Data Index: 433469 (The Pile)

Max Activating Token Index: 151