Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 797 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0392. Min Range: -1.0392

Max Act: 1.0392. Min Act: -0.0000

Data Index: 1849228 (The Pile)

Max Activating Token Index: 574

Text #1

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.8677. Min Act: -0.0000

Data Index: 197977 (The Pile)

Max Activating Token Index: 370

Text #2

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1056212 (The Pile)

Max Activating Token Index: 1006

Text #3

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1902710 (The Pile)

Max Activating Token Index: 313

Text #4

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7560. Min Act: -0.0000

Data Index: 105678 (The Pile)

Max Activating Token Index: 367

Text #5

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7632. Min Act: -0.0000

Data Index: 240054 (The Pile)

Max Activating Token Index: 202

Text #6

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7470. Min Act: -0.0000

Data Index: 1367865 (The Pile)

Max Activating Token Index: 747

Text #7

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.6817. Min Act: -0.0000

Data Index: 431930 (The Pile)

Max Activating Token Index: 519

Text #8

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.6443. Min Act: -0.0000

Data Index: 854657 (The Pile)

Max Activating Token Index: 496

Text #9

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7445. Min Act: -0.0000

Data Index: 754705 (The Pile)

Max Activating Token Index: 430

Text #10

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.6465. Min Act: -0.0000

Data Index: 1621726 (The Pile)

Max Activating Token Index: 910

Text #11

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7211. Min Act: -0.0000

Data Index: 1850696 (The Pile)

Max Activating Token Index: 269

Text #12

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.6650. Min Act: -0.0000

Data Index: 492655 (The Pile)

Max Activating Token Index: 961

Text #13

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.5830. Min Act: -0.0000

Data Index: 757842 (The Pile)

Max Activating Token Index: 306

Text #14

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.6623. Min Act: -0.0000

Data Index: 1438673 (The Pile)

Max Activating Token Index: 241

Text #15

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.6526. Min Act: -0.0000

Data Index: 999399 (The Pile)

Max Activating Token Index: 945

Text #16

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.6402. Min Act: -0.0000

Data Index: 876669 (The Pile)

Max Activating Token Index: 520

Text #17

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.6403. Min Act: -0.0000

Data Index: 778380 (The Pile)

Max Activating Token Index: 637

Text #18

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1559050 (The Pile)

Max Activating Token Index: 686

Text #19

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.6169. Min Act: -0.0000

Data Index: 1345653 (The Pile)

Max Activating Token Index: 264