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

Dataset: The Pile

Neuron 1555 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: 0.9584. Min Range: -0.9584

Max Act: 0.9574. Min Act: -0.0000

Data Index: 564599 (The Pile)

Max Activating Token Index: 593

Text #1

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.9584. Min Act: -0.0000

Data Index: 1263528 (The Pile)

Max Activating Token Index: 166

Text #2

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1534383 (The Pile)

Max Activating Token Index: 275

Text #3

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.7734. Min Act: -0.0000

Data Index: 1333209 (The Pile)

Max Activating Token Index: 202

Text #4

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1645108 (The Pile)

Max Activating Token Index: 319

Text #5

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1030791 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.7609. Min Act: -0.0000

Data Index: 209735 (The Pile)

Max Activating Token Index: 401

Text #7

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1139347 (The Pile)

Max Activating Token Index: 466

Text #8

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1966000 (The Pile)

Max Activating Token Index: 190

Text #9

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1642050 (The Pile)

Max Activating Token Index: 420

Text #10

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.6065. Min Act: -0.0000

Data Index: 69662 (The Pile)

Max Activating Token Index: 315

Text #11

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.5235. Min Act: -0.0000

Data Index: 1077322 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1370274 (The Pile)

Max Activating Token Index: 546

Text #13

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1573138 (The Pile)

Max Activating Token Index: 766

Text #14

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.5246. Min Act: -0.0000

Data Index: 475107 (The Pile)

Max Activating Token Index: 733

Text #15

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.5944. Min Act: -0.0000

Data Index: 442550 (The Pile)

Max Activating Token Index: 860

Text #16

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.5563. Min Act: -0.0000

Data Index: 1235572 (The Pile)

Max Activating Token Index: 308

Text #17

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.5086. Min Act: -0.0001

Data Index: 1063291 (The Pile)

Max Activating Token Index: 95

Text #18

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.5294. Min Act: -0.0001

Data Index: 1994085 (The Pile)

Max Activating Token Index: 414

Text #19

Max Range: 0.9584. Min Range: -0.9584

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1990882 (The Pile)

Max Activating Token Index: 376