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

Dataset: The Pile

Neuron 2661 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7195. Min Range: -3.7195

Max Act: 3.6341. Min Act: -0.0000

Data Index: 459150 (The Pile)

Max Activating Token Index: 676

Text #1

Max Range: 3.7195. Min Range: -3.7195

Max Act: 3.7195. Min Act: -0.0000

Data Index: 1466776 (The Pile)

Max Activating Token Index: 166

Text #2

Max Range: 3.7195. Min Range: -3.7195

Max Act: 3.6539. Min Act: -0.0000

Data Index: 1068728 (The Pile)

Max Activating Token Index: 147

Text #3

Max Range: 3.7195. Min Range: -3.7195

Max Act: 3.2802. Min Act: -0.0000

Data Index: 815280 (The Pile)

Max Activating Token Index: 374

Text #4

Max Range: 3.7195. Min Range: -3.7195

Max Act: 3.1463. Min Act: -0.0000

Data Index: 13132 (The Pile)

Max Activating Token Index: 917

Text #5

Max Range: 3.7195. Min Range: -3.7195

Max Act: 3.0726. Min Act: -0.0000

Data Index: 1247780 (The Pile)

Max Activating Token Index: 433

Text #6

Max Range: 3.7195. Min Range: -3.7195

Max Act: 3.6299. Min Act: -0.0000

Data Index: 437346 (The Pile)

Max Activating Token Index: 624

Text #7

Max Range: 3.7195. Min Range: -3.7195

Max Act: 2.8283. Min Act: -0.0000

Data Index: 519663 (The Pile)

Max Activating Token Index: 953

Text #8

Max Range: 3.7195. Min Range: -3.7195

Max Act: 3.0054. Min Act: -0.0000

Data Index: 1702688 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 3.7195. Min Range: -3.7195

Max Act: 2.9427. Min Act: -0.0000

Data Index: 1598229 (The Pile)

Max Activating Token Index: 830

Text #10

Max Range: 3.7195. Min Range: -3.7195

Max Act: 2.7938. Min Act: -0.0000

Data Index: 1115630 (The Pile)

Max Activating Token Index: 176

Text #11

Max Range: 3.7195. Min Range: -3.7195

Max Act: 2.8398. Min Act: -0.0000

Data Index: 151259 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 3.7195. Min Range: -3.7195

Max Act: 2.8230. Min Act: -0.0000

Data Index: 219851 (The Pile)

Max Activating Token Index: 323

Text #13

Max Range: 3.7195. Min Range: -3.7195

Max Act: 2.6699. Min Act: -0.0000

Data Index: 1295981 (The Pile)

Max Activating Token Index: 101

Text #14

Max Range: 3.7195. Min Range: -3.7195

Max Act: 2.7686. Min Act: -0.0000

Data Index: 635431 (The Pile)

Max Activating Token Index: 287

Text #15

Max Range: 3.7195. Min Range: -3.7195

Max Act: 2.9142. Min Act: -0.0000

Data Index: 305222 (The Pile)

Max Activating Token Index: 513

Text #16

Max Range: 3.7195. Min Range: -3.7195

Max Act: 2.8111. Min Act: -0.0000

Data Index: 349976 (The Pile)

Max Activating Token Index: 878

Text #17

Max Range: 3.7195. Min Range: -3.7195

Max Act: 2.7683. Min Act: -0.0000

Data Index: 178606 (The Pile)

Max Activating Token Index: 604

Text #18

Max Range: 3.7195. Min Range: -3.7195

Max Act: 2.7536. Min Act: -0.0000

Data Index: 1471827 (The Pile)

Max Activating Token Index: 764

Text #19

Max Range: 3.7195. Min Range: -3.7195

Max Act: 2.5838. Min Act: -0.0000

Data Index: 378126 (The Pile)

Max Activating Token Index: 462