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

Dataset: The Pile

Neuron 930 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.8172. Min Act: -0.0000

Data Index: 929115 (The Pile)

Max Activating Token Index: 618

Text #1

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.7156. Min Act: -0.0000

Data Index: 1219469 (The Pile)

Max Activating Token Index: 432

Text #2

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.7007. Min Act: -0.0000

Data Index: 1109147 (The Pile)

Max Activating Token Index: 902

Text #3

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.2132. Min Act: -0.0000

Data Index: 633883 (The Pile)

Max Activating Token Index: 914

Text #4

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.4328. Min Act: -0.0000

Data Index: 1379340 (The Pile)

Max Activating Token Index: 593

Text #5

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.3497. Min Act: -0.0000

Data Index: 472839 (The Pile)

Max Activating Token Index: 765

Text #6

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.1772. Min Act: -0.0000

Data Index: 1889403 (The Pile)

Max Activating Token Index: 941

Text #7

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.3381. Min Act: -0.0000

Data Index: 1310536 (The Pile)

Max Activating Token Index: 375

Text #8

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.3353. Min Act: -0.0000

Data Index: 843733 (The Pile)

Max Activating Token Index: 357

Text #9

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.2973. Min Act: -0.0000

Data Index: 513342 (The Pile)

Max Activating Token Index: 472

Text #10

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.2512. Min Act: -0.0000

Data Index: 218495 (The Pile)

Max Activating Token Index: 272

Text #11

Max Range: 3.8172. Min Range: -3.8172

Max Act: 2.9563. Min Act: -0.0000

Data Index: 1647292 (The Pile)

Max Activating Token Index: 567

Text #12

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.3741. Min Act: -0.0000

Data Index: 1472212 (The Pile)

Max Activating Token Index: 347

Text #13

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.0546. Min Act: -0.0000

Data Index: 614947 (The Pile)

Max Activating Token Index: 953

Text #14

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.3339. Min Act: -0.0000

Data Index: 810029 (The Pile)

Max Activating Token Index: 441

Text #15

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.1762. Min Act: -0.0000

Data Index: 225611 (The Pile)

Max Activating Token Index: 824

Text #16

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.0225. Min Act: -0.0000

Data Index: 369087 (The Pile)

Max Activating Token Index: 971

Text #17

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.3199. Min Act: -0.0000

Data Index: 1146098 (The Pile)

Max Activating Token Index: 419

Text #18

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.0148. Min Act: -0.0000

Data Index: 854335 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.1158. Min Act: -0.0000

Data Index: 101025 (The Pile)

Max Activating Token Index: 866