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

Dataset: The Pile

Neuron 2289 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.2836. Min Act: -0.0000

Data Index: 754221 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.3124. Min Act: -0.0000

Data Index: 1409022 (The Pile)

Max Activating Token Index: 680

Text #2

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.3503. Min Act: -0.0000

Data Index: 1201521 (The Pile)

Max Activating Token Index: 799

Text #3

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1790291 (The Pile)

Max Activating Token Index: 854

Text #4

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.2306. Min Act: -0.0000

Data Index: 1491448 (The Pile)

Max Activating Token Index: 220

Text #5

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.2381. Min Act: -0.0000

Data Index: 753058 (The Pile)

Max Activating Token Index: 153

Text #6

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.1288. Min Act: -0.0000

Data Index: 1159628 (The Pile)

Max Activating Token Index: 364

Text #7

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.0033. Min Act: -0.0000

Data Index: 493441 (The Pile)

Max Activating Token Index: 924

Text #8

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.2404. Min Act: -0.0000

Data Index: 451863 (The Pile)

Max Activating Token Index: 847

Text #9

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.9907. Min Act: -0.0000

Data Index: 464734 (The Pile)

Max Activating Token Index: 937

Text #10

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.0376. Min Act: -0.0000

Data Index: 1104618 (The Pile)

Max Activating Token Index: 217

Text #11

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.1043. Min Act: -0.0000

Data Index: 280673 (The Pile)

Max Activating Token Index: 961

Text #12

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.9661. Min Act: -0.0000

Data Index: 1366194 (The Pile)

Max Activating Token Index: 627

Text #13

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.0255. Min Act: -0.0000

Data Index: 1448155 (The Pile)

Max Activating Token Index: 724

Text #14

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.8453. Min Act: -0.0000

Data Index: 1526577 (The Pile)

Max Activating Token Index: 712

Text #15

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.9725. Min Act: -0.0000

Data Index: 1342359 (The Pile)

Max Activating Token Index: 507

Text #16

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.8603. Min Act: -0.0000

Data Index: 347710 (The Pile)

Max Activating Token Index: 295

Text #17

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1982362 (The Pile)

Max Activating Token Index: 376

Text #18

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.9553. Min Act: -0.0000

Data Index: 999138 (The Pile)

Max Activating Token Index: 167

Text #19

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.9849. Min Act: -0.0000

Data Index: 1080921 (The Pile)

Max Activating Token Index: 558