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

Dataset: The Pile

Neuron 2728 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.9618. Min Act: -0.0000

Data Index: 1621571 (The Pile)

Max Activating Token Index: 823

Text #1

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.8220. Min Act: -0.0000

Data Index: 1450531 (The Pile)

Max Activating Token Index: 505

Text #2

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.8059. Min Act: -0.0000

Data Index: 1555371 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.6250. Min Act: -0.0000

Data Index: 1850722 (The Pile)

Max Activating Token Index: 120

Text #4

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.2349. Min Act: -0.0000

Data Index: 1575363 (The Pile)

Max Activating Token Index: 745

Text #5

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.2420. Min Act: -0.0000

Data Index: 1796023 (The Pile)

Max Activating Token Index: 96

Text #6

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.2070. Min Act: -0.0000

Data Index: 203458 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.1851. Min Act: -0.0000

Data Index: 59205 (The Pile)

Max Activating Token Index: 391

Text #8

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.0987. Min Act: -0.0000

Data Index: 1633158 (The Pile)

Max Activating Token Index: 701

Text #9

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.1047. Min Act: -0.0000

Data Index: 306739 (The Pile)

Max Activating Token Index: 613

Text #10

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.1159. Min Act: -0.0000

Data Index: 152952 (The Pile)

Max Activating Token Index: 831

Text #11

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.1029. Min Act: -0.0000

Data Index: 1217406 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.1360. Min Act: -0.0000

Data Index: 1156057 (The Pile)

Max Activating Token Index: 39

Text #13

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.0888. Min Act: -0.0000

Data Index: 1923359 (The Pile)

Max Activating Token Index: 148

Text #14

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.0572. Min Act: -0.0000

Data Index: 416395 (The Pile)

Max Activating Token Index: 253

Text #15

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.0961. Min Act: -0.0000

Data Index: 325947 (The Pile)

Max Activating Token Index: 615

Text #16

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.0681. Min Act: -0.0000

Data Index: 144843 (The Pile)

Max Activating Token Index: 736

Text #17

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.0785. Min Act: -0.0000

Data Index: 1922949 (The Pile)

Max Activating Token Index: 288

Text #18

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.1138. Min Act: -0.0000

Data Index: 1184608 (The Pile)

Max Activating Token Index: 863

Text #19

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.0444. Min Act: -0.0000

Data Index: 1552084 (The Pile)

Max Activating Token Index: 195