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

Dataset: The Pile

Neuron 496 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.4238. Min Act: -0.0000

Data Index: 479676 (The Pile)

Max Activating Token Index: 28

Text #1

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.2395. Min Act: -0.0000

Data Index: 1383069 (The Pile)

Max Activating Token Index: 379

Text #2

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.2149. Min Act: -0.0000

Data Index: 1784896 (The Pile)

Max Activating Token Index: 426

Text #3

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.3829. Min Act: -0.0000

Data Index: 850882 (The Pile)

Max Activating Token Index: 628

Text #4

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.2121. Min Act: -0.0000

Data Index: 1940450 (The Pile)

Max Activating Token Index: 19

Text #5

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.1113. Min Act: -0.0000

Data Index: 1780353 (The Pile)

Max Activating Token Index: 258

Text #6

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1971066 (The Pile)

Max Activating Token Index: 519

Text #7

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.0862. Min Act: -0.0000

Data Index: 1356818 (The Pile)

Max Activating Token Index: 1001

Text #8

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.0711. Min Act: -0.0000

Data Index: 396779 (The Pile)

Max Activating Token Index: 209

Text #9

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.1092. Min Act: -0.0000

Data Index: 1552180 (The Pile)

Max Activating Token Index: 228

Text #10

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.0342. Min Act: -0.0000

Data Index: 1790182 (The Pile)

Max Activating Token Index: 505

Text #11

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.0022. Min Act: -0.0001

Data Index: 1685942 (The Pile)

Max Activating Token Index: 929

Text #12

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.0513. Min Act: -0.0000

Data Index: 600339 (The Pile)

Max Activating Token Index: 544

Text #13

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1921696 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.9869. Min Act: -0.0000

Data Index: 1637190 (The Pile)

Max Activating Token Index: 299

Text #15

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.1476. Min Act: -0.0000

Data Index: 315667 (The Pile)

Max Activating Token Index: 958

Text #16

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.9714. Min Act: -0.0000

Data Index: 266428 (The Pile)

Max Activating Token Index: 640

Text #17

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.9993. Min Act: -0.0000

Data Index: 696539 (The Pile)

Max Activating Token Index: 114

Text #18

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.0083. Min Act: -0.0000

Data Index: 1144903 (The Pile)

Max Activating Token Index: 565

Text #19

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.9232. Min Act: -0.0000

Data Index: 1735643 (The Pile)

Max Activating Token Index: 20