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

Dataset: The Pile

Neuron 245 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: 1.4308. Min Range: -1.4308

Max Act: 1.4308. Min Act: -0.0000

Data Index: 593429 (The Pile)

Max Activating Token Index: 434

Text #1

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.9441. Min Act: -0.0000

Data Index: 1417931 (The Pile)

Max Activating Token Index: 202

Text #2

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.8591. Min Act: -0.0000

Data Index: 278323 (The Pile)

Max Activating Token Index: 690

Text #3

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1973353 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1149171 (The Pile)

Max Activating Token Index: 324

Text #5

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1993528 (The Pile)

Max Activating Token Index: 173

Text #6

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.7625. Min Act: -0.0000

Data Index: 191652 (The Pile)

Max Activating Token Index: 965

Text #7

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1061460 (The Pile)

Max Activating Token Index: 311

Text #8

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.7396. Min Act: -0.0000

Data Index: 167472 (The Pile)

Max Activating Token Index: 515

Text #9

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1851283 (The Pile)

Max Activating Token Index: 346

Text #10

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.6647. Min Act: -0.0000

Data Index: 428086 (The Pile)

Max Activating Token Index: 541

Text #11

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.6724. Min Act: -0.0000

Data Index: 1516610 (The Pile)

Max Activating Token Index: 929

Text #12

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.6347. Min Act: -0.0000

Data Index: 312486 (The Pile)

Max Activating Token Index: 740

Text #13

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.6283. Min Act: -0.0000

Data Index: 437022 (The Pile)

Max Activating Token Index: 379

Text #14

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.6349. Min Act: -0.0000

Data Index: 16349 (The Pile)

Max Activating Token Index: 827

Text #15

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.6118. Min Act: -0.0000

Data Index: 528236 (The Pile)

Max Activating Token Index: 273

Text #16

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.6099. Min Act: 0.0000

Data Index: 11591 (The Pile)

Max Activating Token Index: 428

Text #17

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1768007 (The Pile)

Max Activating Token Index: 332

Text #18

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1750829 (The Pile)

Max Activating Token Index: 864

Text #19

Max Range: 1.4308. Min Range: -1.4308

Max Act: 0.5666. Min Act: -0.0000

Data Index: 582749 (The Pile)

Max Activating Token Index: 181