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

Dataset: The Pile

Neuron 3532 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: 1.3380. Min Range: -1.3380

Max Act: 1.3380. Min Act: -0.0000

Data Index: 1288205 (The Pile)

Max Activating Token Index: 440

Text #1

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.0397. Min Act: -0.0000

Data Index: 542862 (The Pile)

Max Activating Token Index: 148

Text #2

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.0059. Min Act: -0.0000

Data Index: 1701952 (The Pile)

Max Activating Token Index: 197

Text #3

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.9970. Min Act: -0.0000

Data Index: 414214 (The Pile)

Max Activating Token Index: 460

Text #4

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.9505. Min Act: -0.0000

Data Index: 815852 (The Pile)

Max Activating Token Index: 543

Text #5

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1274683 (The Pile)

Max Activating Token Index: 819

Text #6

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1426969 (The Pile)

Max Activating Token Index: 293

Text #7

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.9240. Min Act: -0.0000

Data Index: 10731 (The Pile)

Max Activating Token Index: 647

Text #8

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.9232. Min Act: -0.0000

Data Index: 12830 (The Pile)

Max Activating Token Index: 429

Text #9

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8832. Min Act: -0.0000

Data Index: 144776 (The Pile)

Max Activating Token Index: 395

Text #10

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8288. Min Act: -0.0000

Data Index: 1936563 (The Pile)

Max Activating Token Index: 177

Text #11

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1640816 (The Pile)

Max Activating Token Index: 744

Text #12

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8373. Min Act: -0.0000

Data Index: 554629 (The Pile)

Max Activating Token Index: 657

Text #13

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8364. Min Act: -0.0000

Data Index: 293962 (The Pile)

Max Activating Token Index: 571

Text #14

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7639. Min Act: 0.0000

Data Index: 149015 (The Pile)

Max Activating Token Index: 349

Text #15

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1968691 (The Pile)

Max Activating Token Index: 426

Text #16

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1453992 (The Pile)

Max Activating Token Index: 529

Text #17

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8156. Min Act: -0.0000

Data Index: 954073 (The Pile)

Max Activating Token Index: 116

Text #18

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8253. Min Act: -0.0000

Data Index: 765913 (The Pile)

Max Activating Token Index: 796

Text #19

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7678. Min Act: -0.0000

Data Index: 1763158 (The Pile)

Max Activating Token Index: 720