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

Dataset: The Pile

Neuron 2980 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: 1.3613. Min Range: -1.3613

Max Act: 1.3201. Min Act: -0.0000

Data Index: 1989787 (The Pile)

Max Activating Token Index: 476

Text #1

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.3613. Min Act: -0.0000

Data Index: 345246 (The Pile)

Max Activating Token Index: 269

Text #2

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.3444. Min Act: -0.0000

Data Index: 1625187 (The Pile)

Max Activating Token Index: 186

Text #3

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.2451. Min Act: -0.0000

Data Index: 1028430 (The Pile)

Max Activating Token Index: 449

Text #4

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.2650. Min Act: -0.0000

Data Index: 1332397 (The Pile)

Max Activating Token Index: 199

Text #5

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.2234. Min Act: -0.0000

Data Index: 1848872 (The Pile)

Max Activating Token Index: 320

Text #6

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.3305. Min Act: -0.0000

Data Index: 816082 (The Pile)

Max Activating Token Index: 24

Text #7

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.2126. Min Act: -0.0000

Data Index: 679200 (The Pile)

Max Activating Token Index: 375

Text #8

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.2373. Min Act: -0.0000

Data Index: 1909188 (The Pile)

Max Activating Token Index: 292

Text #9

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.2766. Min Act: -0.0000

Data Index: 142839 (The Pile)

Max Activating Token Index: 92

Text #10

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.2771. Min Act: -0.0000

Data Index: 369576 (The Pile)

Max Activating Token Index: 295

Text #11

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.2368. Min Act: -0.0000

Data Index: 578139 (The Pile)

Max Activating Token Index: 286

Text #12

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.2293. Min Act: -0.0000

Data Index: 834853 (The Pile)

Max Activating Token Index: 250

Text #13

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.2549. Min Act: -0.0000

Data Index: 392027 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.2358. Min Act: -0.0000

Data Index: 315603 (The Pile)

Max Activating Token Index: 265

Text #15

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.2404. Min Act: -0.0000

Data Index: 1218895 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.2977. Min Act: -0.0000

Data Index: 599227 (The Pile)

Max Activating Token Index: 285

Text #17

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.2228. Min Act: -0.0000

Data Index: 444880 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.2340. Min Act: -0.0000

Data Index: 721138 (The Pile)

Max Activating Token Index: 488

Text #19

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.2577. Min Act: -0.0000

Data Index: 501605 (The Pile)

Max Activating Token Index: 467