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

Dataset: The Pile

Neuron 1260 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: 1.8031. Min Range: -1.8031

Max Act: 1.8031. Min Act: -0.0000

Data Index: 1332512 (The Pile)

Max Activating Token Index: 491

Text #1

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.4562. Min Act: -0.0000

Data Index: 1860357 (The Pile)

Max Activating Token Index: 634

Text #2

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.4388. Min Act: -0.0000

Data Index: 1008284 (The Pile)

Max Activating Token Index: 630

Text #3

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.4998. Min Act: -0.0000

Data Index: 28440 (The Pile)

Max Activating Token Index: 240

Text #4

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.4774. Min Act: -0.0000

Data Index: 1810215 (The Pile)

Max Activating Token Index: 167

Text #5

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1108165 (The Pile)

Max Activating Token Index: 386

Text #6

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.1905. Min Act: -0.0000

Data Index: 1583843 (The Pile)

Max Activating Token Index: 909

Text #7

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.4156. Min Act: -0.0000

Data Index: 981732 (The Pile)

Max Activating Token Index: 585

Text #8

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.2128. Min Act: -0.0000

Data Index: 548199 (The Pile)

Max Activating Token Index: 675

Text #9

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.2834. Min Act: -0.0000

Data Index: 1760251 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.4241. Min Act: -0.0000

Data Index: 363217 (The Pile)

Max Activating Token Index: 424

Text #11

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.3285. Min Act: -0.0000

Data Index: 1985716 (The Pile)

Max Activating Token Index: 478

Text #12

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.2078. Min Act: -0.0000

Data Index: 940435 (The Pile)

Max Activating Token Index: 537

Text #13

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.2134. Min Act: -0.0000

Data Index: 1064528 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.3203. Min Act: -0.0000

Data Index: 277983 (The Pile)

Max Activating Token Index: 619

Text #15

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.4703. Min Act: -0.0000

Data Index: 1038899 (The Pile)

Max Activating Token Index: 786

Text #16

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.2302. Min Act: -0.0000

Data Index: 387480 (The Pile)

Max Activating Token Index: 420

Text #17

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.2324. Min Act: -0.0000

Data Index: 265510 (The Pile)

Max Activating Token Index: 373

Text #18

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.2255. Min Act: -0.0000

Data Index: 1456016 (The Pile)

Max Activating Token Index: 335

Text #19

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.3660. Min Act: -0.0000

Data Index: 559810 (The Pile)

Max Activating Token Index: 191