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

Dataset: The Pile

Neuron 2807 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: 1.2280. Min Range: -1.2280

Max Act: 1.0775. Min Act: -0.0000

Data Index: 1770501 (The Pile)

Max Activating Token Index: 25

Text #1

Max Range: 1.2280. Min Range: -1.2280

Max Act: 1.0348. Min Act: -0.0000

Data Index: 698681 (The Pile)

Max Activating Token Index: 500

Text #2

Max Range: 1.2280. Min Range: -1.2280

Max Act: 1.0877. Min Act: 0.0000

Data Index: 1187635 (The Pile)

Max Activating Token Index: 143

Text #3

Max Range: 1.2280. Min Range: -1.2280

Max Act: 1.2280. Min Act: -0.0000

Data Index: 561575 (The Pile)

Max Activating Token Index: 166

Text #4

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.9391. Min Act: -0.0000

Data Index: 1208005 (The Pile)

Max Activating Token Index: 803

Text #5

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.9959. Min Act: -0.0000

Data Index: 1470997 (The Pile)

Max Activating Token Index: 45

Text #6

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.9014. Min Act: -0.0000

Data Index: 1628028 (The Pile)

Max Activating Token Index: 224

Text #7

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.9397. Min Act: -0.0000

Data Index: 300061 (The Pile)

Max Activating Token Index: 1001

Text #8

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.9528. Min Act: -0.0000

Data Index: 1542619 (The Pile)

Max Activating Token Index: 6

Text #9

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.9912. Min Act: -0.0000

Data Index: 333891 (The Pile)

Max Activating Token Index: 668

Text #10

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1440457 (The Pile)

Max Activating Token Index: 50

Text #11

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.8311. Min Act: -0.0000

Data Index: 796416 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.8756. Min Act: -0.0000

Data Index: 1264588 (The Pile)

Max Activating Token Index: 359

Text #13

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.7288. Min Act: -0.0000

Data Index: 544112 (The Pile)

Max Activating Token Index: 66

Text #14

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.8257. Min Act: -0.0000

Data Index: 461943 (The Pile)

Max Activating Token Index: 632

Text #15

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1983831 (The Pile)

Max Activating Token Index: 705

Text #16

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.8046. Min Act: -0.0000

Data Index: 88068 (The Pile)

Max Activating Token Index: 552

Text #17

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.7572. Min Act: -0.0000

Data Index: 720106 (The Pile)

Max Activating Token Index: 408

Text #18

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.7437. Min Act: -0.0000

Data Index: 775880 (The Pile)

Max Activating Token Index: 873

Text #19

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.6669. Min Act: -0.0000

Data Index: 969263 (The Pile)

Max Activating Token Index: 897