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

Dataset: The Pile

Neuron 4058 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: 4.6225. Min Range: -4.6225

Max Act: 4.6225. Min Act: -0.0000

Data Index: 1167913 (The Pile)

Max Activating Token Index: 193

Text #1

Max Range: 4.6225. Min Range: -4.6225

Max Act: 3.9796. Min Act: -0.0000

Data Index: 1757044 (The Pile)

Max Activating Token Index: 501

Text #2

Max Range: 4.6225. Min Range: -4.6225

Max Act: 3.6018. Min Act: -0.0000

Data Index: 764984 (The Pile)

Max Activating Token Index: 121

Text #3

Max Range: 4.6225. Min Range: -4.6225

Max Act: 3.7129. Min Act: -0.0000

Data Index: 479209 (The Pile)

Max Activating Token Index: 53

Text #4

Max Range: 4.6225. Min Range: -4.6225

Max Act: 3.9974. Min Act: -0.0000

Data Index: 481881 (The Pile)

Max Activating Token Index: 138

Text #5

Max Range: 4.6225. Min Range: -4.6225

Max Act: 3.5051. Min Act: -0.0000

Data Index: 1026420 (The Pile)

Max Activating Token Index: 168

Text #6

Max Range: 4.6225. Min Range: -4.6225

Max Act: 3.4686. Min Act: -0.0000

Data Index: 1147743 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 4.6225. Min Range: -4.6225

Max Act: 3.2530. Min Act: -0.0000

Data Index: 1221552 (The Pile)

Max Activating Token Index: 333

Text #8

Max Range: 4.6225. Min Range: -4.6225

Max Act: 3.1231. Min Act: -0.0000

Data Index: 1205124 (The Pile)

Max Activating Token Index: 155

Text #9

Max Range: 4.6225. Min Range: -4.6225

Max Act: 3.3542. Min Act: -0.0000

Data Index: 592480 (The Pile)

Max Activating Token Index: 120

Text #10

Max Range: 4.6225. Min Range: -4.6225

Max Act: 3.0213. Min Act: -0.0000

Data Index: 1647902 (The Pile)

Max Activating Token Index: 398

Text #11

Max Range: 4.6225. Min Range: -4.6225

Max Act: 3.1628. Min Act: -0.0000

Data Index: 1487727 (The Pile)

Max Activating Token Index: 501

Text #12

Max Range: 4.6225. Min Range: -4.6225

Max Act: 3.3061. Min Act: -0.0000

Data Index: 599567 (The Pile)

Max Activating Token Index: 245

Text #13

Max Range: 4.6225. Min Range: -4.6225

Max Act: 3.1039. Min Act: -0.0000

Data Index: 1507919 (The Pile)

Max Activating Token Index: 505

Text #14

Max Range: 4.6225. Min Range: -4.6225

Max Act: 2.9339. Min Act: -0.0000

Data Index: 600530 (The Pile)

Max Activating Token Index: 424

Text #15

Max Range: 4.6225. Min Range: -4.6225

Max Act: 2.9438. Min Act: -0.0000

Data Index: 1894011 (The Pile)

Max Activating Token Index: 369

Text #16

Max Range: 4.6225. Min Range: -4.6225

Max Act: 2.7765. Min Act: -0.0000

Data Index: 862557 (The Pile)

Max Activating Token Index: 167

Text #17

Max Range: 4.6225. Min Range: -4.6225

Max Act: 3.0504. Min Act: -0.0000

Data Index: 1244447 (The Pile)

Max Activating Token Index: 133

Text #18

Max Range: 4.6225. Min Range: -4.6225

Max Act: 3.0546. Min Act: -0.0000

Data Index: 1641042 (The Pile)

Max Activating Token Index: 654

Text #19

Max Range: 4.6225. Min Range: -4.6225

Max Act: 2.7171. Min Act: -0.0000

Data Index: 179211 (The Pile)

Max Activating Token Index: 645