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

Dataset: The Pile

Neuron 2002 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.5505. Min Range: -3.5505

Max Act: 3.5505. Min Act: -0.0000

Data Index: 721951 (The Pile)

Max Activating Token Index: 154

Text #1

Max Range: 3.5505. Min Range: -3.5505

Max Act: 3.2196. Min Act: -0.0000

Data Index: 1317105 (The Pile)

Max Activating Token Index: 219

Text #2

Max Range: 3.5505. Min Range: -3.5505

Max Act: 2.8701. Min Act: -0.0000

Data Index: 422616 (The Pile)

Max Activating Token Index: 433

Text #3

Max Range: 3.5505. Min Range: -3.5505

Max Act: 3.1193. Min Act: -0.0000

Data Index: 108037 (The Pile)

Max Activating Token Index: 153

Text #4

Max Range: 3.5505. Min Range: -3.5505

Max Act: 2.6345. Min Act: -0.0000

Data Index: 1100462 (The Pile)

Max Activating Token Index: 188

Text #5

Max Range: 3.5505. Min Range: -3.5505

Max Act: 2.6767. Min Act: -0.0000

Data Index: 902580 (The Pile)

Max Activating Token Index: 455

Text #6

Max Range: 3.5505. Min Range: -3.5505

Max Act: 2.6530. Min Act: -0.0000

Data Index: 1506661 (The Pile)

Max Activating Token Index: 208

Text #7

Max Range: 3.5505. Min Range: -3.5505

Max Act: 2.6813. Min Act: -0.0000

Data Index: 970663 (The Pile)

Max Activating Token Index: 475

Text #8

Max Range: 3.5505. Min Range: -3.5505

Max Act: 2.6859. Min Act: -0.0000

Data Index: 1405095 (The Pile)

Max Activating Token Index: 225

Text #9

Max Range: 3.5505. Min Range: -3.5505

Max Act: 2.6738. Min Act: -0.0000

Data Index: 330014 (The Pile)

Max Activating Token Index: 816

Text #10

Max Range: 3.5505. Min Range: -3.5505

Max Act: 2.7952. Min Act: -0.0000

Data Index: 230581 (The Pile)

Max Activating Token Index: 191

Text #11

Max Range: 3.5505. Min Range: -3.5505

Max Act: 2.4999. Min Act: -0.0000

Data Index: 207465 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 3.5505. Min Range: -3.5505

Max Act: 2.7473. Min Act: -0.0000

Data Index: 273115 (The Pile)

Max Activating Token Index: 860

Text #13

Max Range: 3.5505. Min Range: -3.5505

Max Act: 2.7348. Min Act: -0.0000

Data Index: 41475 (The Pile)

Max Activating Token Index: 439

Text #14

Max Range: 3.5505. Min Range: -3.5505

Max Act: 2.3408. Min Act: -0.0000

Data Index: 870760 (The Pile)

Max Activating Token Index: 600

Text #15

Max Range: 3.5505. Min Range: -3.5505

Max Act: 2.7157. Min Act: -0.0000

Data Index: 806031 (The Pile)

Max Activating Token Index: 628

Text #16

Max Range: 3.5505. Min Range: -3.5505

Max Act: 2.5490. Min Act: -0.0000

Data Index: 1130876 (The Pile)

Max Activating Token Index: 92

Text #17

Max Range: 3.5505. Min Range: -3.5505

Max Act: 2.6829. Min Act: -0.0000

Data Index: 1916414 (The Pile)

Max Activating Token Index: 147

Text #18

Max Range: 3.5505. Min Range: -3.5505

Max Act: 2.5489. Min Act: -0.0000

Data Index: 526901 (The Pile)

Max Activating Token Index: 90

Text #19

Max Range: 3.5505. Min Range: -3.5505

Max Act: 2.5529. Min Act: -0.0000

Data Index: 264128 (The Pile)

Max Activating Token Index: 621