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

Dataset: The Pile

Neuron 4524 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.3215. Min Act: -0.0000

Data Index: 1307995 (The Pile)

Max Activating Token Index: 424

Text #1

Max Range: 3.3215. Min Range: -3.3215

Max Act: 2.8518. Min Act: -0.0000

Data Index: 773429 (The Pile)

Max Activating Token Index: 252

Text #2

Max Range: 3.3215. Min Range: -3.3215

Max Act: 2.4596. Min Act: -0.0000

Data Index: 617959 (The Pile)

Max Activating Token Index: 866

Text #3

Max Range: 3.3215. Min Range: -3.3215

Max Act: 2.4388. Min Act: -0.0000

Data Index: 692937 (The Pile)

Max Activating Token Index: 370

Text #4

Max Range: 3.3215. Min Range: -3.3215

Max Act: 2.3873. Min Act: -0.0000

Data Index: 375951 (The Pile)

Max Activating Token Index: 1018

Text #5

Max Range: 3.3215. Min Range: -3.3215

Max Act: 2.2769. Min Act: -0.0000

Data Index: 1409055 (The Pile)

Max Activating Token Index: 837

Text #6

Max Range: 3.3215. Min Range: -3.3215

Max Act: 2.1167. Min Act: -0.0000

Data Index: 1672164 (The Pile)

Max Activating Token Index: 267

Text #7

Max Range: 3.3215. Min Range: -3.3215

Max Act: 2.0855. Min Act: -0.0000

Data Index: 1287524 (The Pile)

Max Activating Token Index: 702

Text #8

Max Range: 3.3215. Min Range: -3.3215

Max Act: 2.0839. Min Act: -0.0000

Data Index: 635598 (The Pile)

Max Activating Token Index: 665

Text #9

Max Range: 3.3215. Min Range: -3.3215

Max Act: 2.2994. Min Act: -0.0000

Data Index: 220677 (The Pile)

Max Activating Token Index: 269

Text #10

Max Range: 3.3215. Min Range: -3.3215

Max Act: 2.1276. Min Act: -0.0000

Data Index: 693654 (The Pile)

Max Activating Token Index: 300

Text #11

Max Range: 3.3215. Min Range: -3.3215

Max Act: 2.0004. Min Act: -0.0000

Data Index: 499812 (The Pile)

Max Activating Token Index: 642

Text #12

Max Range: 3.3215. Min Range: -3.3215

Max Act: 2.0163. Min Act: -0.0000

Data Index: 862461 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 3.3215. Min Range: -3.3215

Max Act: 2.0486. Min Act: -0.0000

Data Index: 1988488 (The Pile)

Max Activating Token Index: 728

Text #14

Max Range: 3.3215. Min Range: -3.3215

Max Act: 1.9331. Min Act: -0.0000

Data Index: 1726350 (The Pile)

Max Activating Token Index: 55

Text #15

Max Range: 3.3215. Min Range: -3.3215

Max Act: 1.8858. Min Act: -0.0000

Data Index: 1833633 (The Pile)

Max Activating Token Index: 476

Text #16

Max Range: 3.3215. Min Range: -3.3215

Max Act: 1.8122. Min Act: -0.0000

Data Index: 285952 (The Pile)

Max Activating Token Index: 286

Text #17

Max Range: 3.3215. Min Range: -3.3215

Max Act: 1.8109. Min Act: -0.0000

Data Index: 1483252 (The Pile)

Max Activating Token Index: 501

Text #18

Max Range: 3.3215. Min Range: -3.3215

Max Act: 1.8998. Min Act: -0.0000

Data Index: 1296508 (The Pile)

Max Activating Token Index: 420

Text #19

Max Range: 3.3215. Min Range: -3.3215

Max Act: 1.6769. Min Act: -0.0000

Data Index: 1792170 (The Pile)

Max Activating Token Index: 597