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

Dataset: The Pile

Neuron 3743 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.8131. Min Act: -0.0000

Data Index: 200527 (The Pile)

Max Activating Token Index: 142

Text #1

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7699. Min Act: -0.0000

Data Index: 221928 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1151106 (The Pile)

Max Activating Token Index: 479

Text #3

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1545741 (The Pile)

Max Activating Token Index: 1011

Text #4

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7504. Min Act: -0.0000

Data Index: 1311401 (The Pile)

Max Activating Token Index: 420

Text #5

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1500935 (The Pile)

Max Activating Token Index: 230

Text #6

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6279. Min Act: -0.0000

Data Index: 365693 (The Pile)

Max Activating Token Index: 534

Text #7

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7191. Min Act: -0.0000

Data Index: 635252 (The Pile)

Max Activating Token Index: 424

Text #8

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1772125 (The Pile)

Max Activating Token Index: 566

Text #9

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7103. Min Act: -0.0000

Data Index: 1209423 (The Pile)

Max Activating Token Index: 281

Text #10

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7734. Min Act: -0.0000

Data Index: 682991 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7339. Min Act: -0.0000

Data Index: 1199635 (The Pile)

Max Activating Token Index: 438

Text #12

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7399. Min Act: -0.0000

Data Index: 1858380 (The Pile)

Max Activating Token Index: 695

Text #13

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1635059 (The Pile)

Max Activating Token Index: 738

Text #14

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6829. Min Act: -0.0000

Data Index: 276739 (The Pile)

Max Activating Token Index: 352

Text #15

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7077. Min Act: -0.0000

Data Index: 341148 (The Pile)

Max Activating Token Index: 510

Text #16

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6771. Min Act: -0.0000

Data Index: 423364 (The Pile)

Max Activating Token Index: 232

Text #17

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7486. Min Act: -0.0000

Data Index: 1076952 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.5681. Min Act: -0.0000

Data Index: 205322 (The Pile)

Max Activating Token Index: 644

Text #19

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6931. Min Act: -0.0000

Data Index: 212111 (The Pile)

Max Activating Token Index: 422