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

Dataset: The Pile

Neuron 1587 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: 3.4585. Min Range: -3.4585

Max Act: 3.4585. Min Act: -0.0000

Data Index: 820740 (The Pile)

Max Activating Token Index: 349

Text #1

Max Range: 3.4585. Min Range: -3.4585

Max Act: 3.1305. Min Act: -0.0000

Data Index: 1339542 (The Pile)

Max Activating Token Index: 431

Text #2

Max Range: 3.4585. Min Range: -3.4585

Max Act: 3.1469. Min Act: -0.0000

Data Index: 1049519 (The Pile)

Max Activating Token Index: 650

Text #3

Max Range: 3.4585. Min Range: -3.4585

Max Act: 3.1558. Min Act: -0.0000

Data Index: 51525 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 3.4585. Min Range: -3.4585

Max Act: 3.0393. Min Act: -0.0000

Data Index: 1981223 (The Pile)

Max Activating Token Index: 249

Text #5

Max Range: 3.4585. Min Range: -3.4585

Max Act: 3.0172. Min Act: -0.0000

Data Index: 1919339 (The Pile)

Max Activating Token Index: 832

Text #6

Max Range: 3.4585. Min Range: -3.4585

Max Act: 3.1654. Min Act: -0.0000

Data Index: 285314 (The Pile)

Max Activating Token Index: 455

Text #7

Max Range: 3.4585. Min Range: -3.4585

Max Act: 3.0113. Min Act: -0.0000

Data Index: 765321 (The Pile)

Max Activating Token Index: 80

Text #8

Max Range: 3.4585. Min Range: -3.4585

Max Act: 2.8534. Min Act: -0.0000

Data Index: 289329 (The Pile)

Max Activating Token Index: 329

Text #9

Max Range: 3.4585. Min Range: -3.4585

Max Act: 2.9865. Min Act: -0.0000

Data Index: 747462 (The Pile)

Max Activating Token Index: 370

Text #10

Max Range: 3.4585. Min Range: -3.4585

Max Act: 2.9947. Min Act: -0.0000

Data Index: 730552 (The Pile)

Max Activating Token Index: 556

Text #11

Max Range: 3.4585. Min Range: -3.4585

Max Act: 2.6589. Min Act: -0.0000

Data Index: 800959 (The Pile)

Max Activating Token Index: 667

Text #12

Max Range: 3.4585. Min Range: -3.4585

Max Act: 3.1299. Min Act: -0.0000

Data Index: 930128 (The Pile)

Max Activating Token Index: 635

Text #13

Max Range: 3.4585. Min Range: -3.4585

Max Act: 2.7520. Min Act: -0.0000

Data Index: 843366 (The Pile)

Max Activating Token Index: 812

Text #14

Max Range: 3.4585. Min Range: -3.4585

Max Act: 2.7928. Min Act: -0.0000

Data Index: 1793836 (The Pile)

Max Activating Token Index: 372

Text #15

Max Range: 3.4585. Min Range: -3.4585

Max Act: 2.5097. Min Act: -0.0000

Data Index: 778547 (The Pile)

Max Activating Token Index: 633

Text #16

Max Range: 3.4585. Min Range: -3.4585

Max Act: 3.1540. Min Act: -0.0000

Data Index: 1265556 (The Pile)

Max Activating Token Index: 746

Text #17

Max Range: 3.4585. Min Range: -3.4585

Max Act: 2.7399. Min Act: -0.0000

Data Index: 1208846 (The Pile)

Max Activating Token Index: 838

Text #18

Max Range: 3.4585. Min Range: -3.4585

Max Act: 2.6078. Min Act: -0.0000

Data Index: 1435365 (The Pile)

Max Activating Token Index: 236

Text #19

Max Range: 3.4585. Min Range: -3.4585

Max Act: 2.6272. Min Act: -0.0000

Data Index: 757678 (The Pile)

Max Activating Token Index: 400