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

Dataset: The Pile

Neuron 34 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1924564 (The Pile)

Max Activating Token Index: 275

Text #1

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1128579 (The Pile)

Max Activating Token Index: 719

Text #2

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1391849 (The Pile)

Max Activating Token Index: 642

Text #3

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2754. Min Act: -0.0000

Data Index: 684919 (The Pile)

Max Activating Token Index: 51

Text #4

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1617275 (The Pile)

Max Activating Token Index: 590

Text #5

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2935. Min Act: -0.0000

Data Index: 1616133 (The Pile)

Max Activating Token Index: 232

Text #6

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2413. Min Act: -0.0000

Data Index: 1036509 (The Pile)

Max Activating Token Index: 587

Text #7

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2576. Min Act: -0.0000

Data Index: 700526 (The Pile)

Max Activating Token Index: 235

Text #8

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2552. Min Act: -0.0000

Data Index: 132325 (The Pile)

Max Activating Token Index: 848

Text #9

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2571. Min Act: -0.0000

Data Index: 280141 (The Pile)

Max Activating Token Index: 368

Text #10

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2801. Min Act: -0.0000

Data Index: 3033 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1616767 (The Pile)

Max Activating Token Index: 172

Text #12

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1954993 (The Pile)

Max Activating Token Index: 435

Text #13

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2351. Min Act: -0.0000

Data Index: 974389 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2170. Min Act: -0.0000

Data Index: 1583851 (The Pile)

Max Activating Token Index: 500

Text #15

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2241. Min Act: -0.0000

Data Index: 1678771 (The Pile)

Max Activating Token Index: 507

Text #16

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2296. Min Act: -0.0000

Data Index: 770329 (The Pile)

Max Activating Token Index: 455

Text #17

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1976197 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1613642 (The Pile)

Max Activating Token Index: 612

Text #19

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1721155 (The Pile)

Max Activating Token Index: 562