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

Dataset: The Pile

Neuron 4973 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: 3.5279. Min Range: -3.5279

Max Act: 3.5279. Min Act: -0.0000

Data Index: 839294 (The Pile)

Max Activating Token Index: 898

Text #1

Max Range: 3.5279. Min Range: -3.5279

Max Act: 3.3903. Min Act: -0.0000

Data Index: 1228742 (The Pile)

Max Activating Token Index: 726

Text #2

Max Range: 3.5279. Min Range: -3.5279

Max Act: 3.0856. Min Act: -0.0000

Data Index: 931241 (The Pile)

Max Activating Token Index: 789

Text #3

Max Range: 3.5279. Min Range: -3.5279

Max Act: 3.4597. Min Act: -0.0000

Data Index: 462243 (The Pile)

Max Activating Token Index: 894

Text #4

Max Range: 3.5279. Min Range: -3.5279

Max Act: 3.3463. Min Act: -0.0000

Data Index: 734994 (The Pile)

Max Activating Token Index: 196

Text #5

Max Range: 3.5279. Min Range: -3.5279

Max Act: 2.9648. Min Act: -0.0000

Data Index: 1527085 (The Pile)

Max Activating Token Index: 563

Text #6

Max Range: 3.5279. Min Range: -3.5279

Max Act: 3.1226. Min Act: -0.0000

Data Index: 416258 (The Pile)

Max Activating Token Index: 747

Text #7

Max Range: 3.5279. Min Range: -3.5279

Max Act: 3.2869. Min Act: -0.0000

Data Index: 6745 (The Pile)

Max Activating Token Index: 745

Text #8

Max Range: 3.5279. Min Range: -3.5279

Max Act: 2.9609. Min Act: -0.0000

Data Index: 889217 (The Pile)

Max Activating Token Index: 682

Text #9

Max Range: 3.5279. Min Range: -3.5279

Max Act: 2.8633. Min Act: -0.0000

Data Index: 1304755 (The Pile)

Max Activating Token Index: 73

Text #10

Max Range: 3.5279. Min Range: -3.5279

Max Act: 3.0176. Min Act: -0.0000

Data Index: 1113354 (The Pile)

Max Activating Token Index: 420

Text #11

Max Range: 3.5279. Min Range: -3.5279

Max Act: 2.9567. Min Act: -0.0000

Data Index: 1684412 (The Pile)

Max Activating Token Index: 685

Text #12

Max Range: 3.5279. Min Range: -3.5279

Max Act: 2.6700. Min Act: -0.0000

Data Index: 1789845 (The Pile)

Max Activating Token Index: 522

Text #13

Max Range: 3.5279. Min Range: -3.5279

Max Act: 2.7931. Min Act: -0.0000

Data Index: 66285 (The Pile)

Max Activating Token Index: 551

Text #14

Max Range: 3.5279. Min Range: -3.5279

Max Act: 2.6579. Min Act: -0.0000

Data Index: 1915184 (The Pile)

Max Activating Token Index: 491

Text #15

Max Range: 3.5279. Min Range: -3.5279

Max Act: 2.6543. Min Act: -0.0000

Data Index: 1243772 (The Pile)

Max Activating Token Index: 398

Text #16

Max Range: 3.5279. Min Range: -3.5279

Max Act: 2.7845. Min Act: -0.0000

Data Index: 399347 (The Pile)

Max Activating Token Index: 562

Text #17

Max Range: 3.5279. Min Range: -3.5279

Max Act: 2.7466. Min Act: -0.0000

Data Index: 1323110 (The Pile)

Max Activating Token Index: 562

Text #18

Max Range: 3.5279. Min Range: -3.5279

Max Act: 2.8902. Min Act: -0.0000

Data Index: 29750 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 3.5279. Min Range: -3.5279

Max Act: 2.7314. Min Act: -0.0000

Data Index: 262445 (The Pile)

Max Activating Token Index: 491