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

Dataset: The Pile

Neuron 3195 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1895396 (The Pile)

Max Activating Token Index: 5

Text #1

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.8370. Min Act: -0.0000

Data Index: 1318070 (The Pile)

Max Activating Token Index: 886

Text #2

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1992712 (The Pile)

Max Activating Token Index: 690

Text #3

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.7539. Min Act: 0.0000

Data Index: 982474 (The Pile)

Max Activating Token Index: 251

Text #4

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.7354. Min Act: -0.0000

Data Index: 208495 (The Pile)

Max Activating Token Index: 695

Text #5

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1549651 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1599496 (The Pile)

Max Activating Token Index: 159

Text #7

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.7827. Min Act: -0.0000

Data Index: 1826059 (The Pile)

Max Activating Token Index: 222

Text #8

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1152237 (The Pile)

Max Activating Token Index: 541

Text #9

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.7145. Min Act: -0.0000

Data Index: 785701 (The Pile)

Max Activating Token Index: 153

Text #10

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6612. Min Act: -0.0000

Data Index: 63507 (The Pile)

Max Activating Token Index: 896

Text #11

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.7073. Min Act: -0.0000

Data Index: 937801 (The Pile)

Max Activating Token Index: 348

Text #12

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6271. Min Act: -0.0000

Data Index: 246735 (The Pile)

Max Activating Token Index: 349

Text #13

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1188344 (The Pile)

Max Activating Token Index: 403

Text #14

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6379. Min Act: -0.0000

Data Index: 1023782 (The Pile)

Max Activating Token Index: 948

Text #15

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6552. Min Act: -0.0000

Data Index: 389084 (The Pile)

Max Activating Token Index: 44

Text #16

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1183342 (The Pile)

Max Activating Token Index: 437

Text #17

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6217. Min Act: -0.0000

Data Index: 269303 (The Pile)

Max Activating Token Index: 243

Text #18

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1897630 (The Pile)

Max Activating Token Index: 934

Text #19

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1401153 (The Pile)

Max Activating Token Index: 388