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

Dataset: The Pile

Neuron 1167 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: 1.8447. Min Range: -1.8447

Max Act: 1.6480. Min Act: -0.0000

Data Index: 84546 (The Pile)

Max Activating Token Index: 427

Text #1

Max Range: 1.8447. Min Range: -1.8447

Max Act: 1.8447. Min Act: -0.0000

Data Index: 289407 (The Pile)

Max Activating Token Index: 715

Text #2

Max Range: 1.8447. Min Range: -1.8447

Max Act: 1.5128. Min Act: -0.0000

Data Index: 732325 (The Pile)

Max Activating Token Index: 363

Text #3

Max Range: 1.8447. Min Range: -1.8447

Max Act: 1.2658. Min Act: -0.0000

Data Index: 765672 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 1.8447. Min Range: -1.8447

Max Act: 1.1856. Min Act: -0.0000

Data Index: 1412235 (The Pile)

Max Activating Token Index: 821

Text #5

Max Range: 1.8447. Min Range: -1.8447

Max Act: 1.3190. Min Act: -0.0000

Data Index: 1304684 (The Pile)

Max Activating Token Index: 203

Text #6

Max Range: 1.8447. Min Range: -1.8447

Max Act: 1.2551. Min Act: -0.0000

Data Index: 824702 (The Pile)

Max Activating Token Index: 86

Text #7

Max Range: 1.8447. Min Range: -1.8447

Max Act: 1.3131. Min Act: -0.0000

Data Index: 753230 (The Pile)

Max Activating Token Index: 385

Text #8

Max Range: 1.8447. Min Range: -1.8447

Max Act: 1.3731. Min Act: -0.0000

Data Index: 737405 (The Pile)

Max Activating Token Index: 615

Text #9

Max Range: 1.8447. Min Range: -1.8447

Max Act: 1.0367. Min Act: -0.0000

Data Index: 703644 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 1.8447. Min Range: -1.8447

Max Act: 1.3760. Min Act: -0.0000

Data Index: 23245 (The Pile)

Max Activating Token Index: 915

Text #11

Max Range: 1.8447. Min Range: -1.8447

Max Act: 1.0316. Min Act: -0.0000

Data Index: 1569876 (The Pile)

Max Activating Token Index: 715

Text #12

Max Range: 1.8447. Min Range: -1.8447

Max Act: 1.7249. Min Act: -0.0000

Data Index: 1242606 (The Pile)

Max Activating Token Index: 663

Text #13

Max Range: 1.8447. Min Range: -1.8447

Max Act: 1.2224. Min Act: -0.0000

Data Index: 228085 (The Pile)

Max Activating Token Index: 596

Text #14

Max Range: 1.8447. Min Range: -1.8447

Max Act: 1.1373. Min Act: -0.0000

Data Index: 575449 (The Pile)

Max Activating Token Index: 580

Text #15

Max Range: 1.8447. Min Range: -1.8447

Max Act: 1.0941. Min Act: -0.0000

Data Index: 1083466 (The Pile)

Max Activating Token Index: 151

Text #16

Max Range: 1.8447. Min Range: -1.8447

Max Act: 1.0171. Min Act: -0.0000

Data Index: 1368963 (The Pile)

Max Activating Token Index: 262

Text #17

Max Range: 1.8447. Min Range: -1.8447

Max Act: 1.1100. Min Act: -0.0000

Data Index: 308858 (The Pile)

Max Activating Token Index: 955

Text #18

Max Range: 1.8447. Min Range: -1.8447

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1589976 (The Pile)

Max Activating Token Index: 818

Text #19

Max Range: 1.8447. Min Range: -1.8447

Max Act: 1.1012. Min Act: -0.0000

Data Index: 896663 (The Pile)

Max Activating Token Index: 678