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

Dataset: The Pile

Neuron 2951 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: 1.5398. Min Range: -1.5398

Max Act: 1.5104. Min Act: -0.0000

Data Index: 1909791 (The Pile)

Max Activating Token Index: 362

Text #1

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.4494. Min Act: -0.0000

Data Index: 229955 (The Pile)

Max Activating Token Index: 369

Text #2

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.4944. Min Act: -0.0000

Data Index: 1093004 (The Pile)

Max Activating Token Index: 561

Text #3

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.4629. Min Act: -0.0000

Data Index: 1514301 (The Pile)

Max Activating Token Index: 301

Text #4

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.4553. Min Act: -0.0000

Data Index: 1625052 (The Pile)

Max Activating Token Index: 63

Text #5

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.3225. Min Act: -0.0000

Data Index: 1994940 (The Pile)

Max Activating Token Index: 255

Text #6

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.3787. Min Act: -0.0000

Data Index: 631344 (The Pile)

Max Activating Token Index: 461

Text #7

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.3774. Min Act: -0.0000

Data Index: 705470 (The Pile)

Max Activating Token Index: 300

Text #8

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.5398. Min Act: -0.0000

Data Index: 894630 (The Pile)

Max Activating Token Index: 767

Text #9

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.3409. Min Act: -0.0000

Data Index: 1034987 (The Pile)

Max Activating Token Index: 415

Text #10

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.3494. Min Act: -0.0000

Data Index: 386135 (The Pile)

Max Activating Token Index: 210

Text #11

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.4299. Min Act: -0.0000

Data Index: 992294 (The Pile)

Max Activating Token Index: 141

Text #12

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.2544. Min Act: -0.0000

Data Index: 536960 (The Pile)

Max Activating Token Index: 347

Text #13

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.3314. Min Act: -0.0000

Data Index: 1227752 (The Pile)

Max Activating Token Index: 377

Text #14

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.2438. Min Act: -0.0000

Data Index: 275110 (The Pile)

Max Activating Token Index: 517

Text #15

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.2908. Min Act: -0.0000

Data Index: 26005 (The Pile)

Max Activating Token Index: 629

Text #16

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.3765. Min Act: -0.0000

Data Index: 1477155 (The Pile)

Max Activating Token Index: 257

Text #17

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.5303. Min Act: -0.0000

Data Index: 648547 (The Pile)

Max Activating Token Index: 523

Text #18

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.1262. Min Act: -0.0000

Data Index: 721551 (The Pile)

Max Activating Token Index: 798

Text #19

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.1857. Min Act: -0.0000

Data Index: 1422210 (The Pile)

Max Activating Token Index: 139