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

Dataset: The Pile

Neuron 5082 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.4126. Min Act: -0.0000

Data Index: 1095874 (The Pile)

Max Activating Token Index: 360

Text #1

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.2132. Min Act: -0.0000

Data Index: 1082998 (The Pile)

Max Activating Token Index: 238

Text #2

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.2180. Min Act: -0.0000

Data Index: 1191623 (The Pile)

Max Activating Token Index: 570

Text #3

Max Range: 1.4126. Min Range: -1.4126

Max Act: 0.8566. Min Act: -0.0000

Data Index: 1071102 (The Pile)

Max Activating Token Index: 643

Text #4

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.0632. Min Act: -0.0000

Data Index: 403195 (The Pile)

Max Activating Token Index: 215

Text #5

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.0374. Min Act: -0.0000

Data Index: 1895621 (The Pile)

Max Activating Token Index: 120

Text #6

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.1182. Min Act: -0.0000

Data Index: 637026 (The Pile)

Max Activating Token Index: 483

Text #7

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.0177. Min Act: -0.0000

Data Index: 679548 (The Pile)

Max Activating Token Index: 186

Text #8

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.0194. Min Act: -0.0000

Data Index: 1145796 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.0827. Min Act: -0.0000

Data Index: 1020968 (The Pile)

Max Activating Token Index: 246

Text #10

Max Range: 1.4126. Min Range: -1.4126

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1978853 (The Pile)

Max Activating Token Index: 367

Text #11

Max Range: 1.4126. Min Range: -1.4126

Max Act: 0.9371. Min Act: -0.0000

Data Index: 1574455 (The Pile)

Max Activating Token Index: 603

Text #12

Max Range: 1.4126. Min Range: -1.4126

Max Act: 0.8666. Min Act: -0.0000

Data Index: 1058682 (The Pile)

Max Activating Token Index: 738

Text #13

Max Range: 1.4126. Min Range: -1.4126

Max Act: 0.9289. Min Act: -0.0000

Data Index: 1389553 (The Pile)

Max Activating Token Index: 623

Text #14

Max Range: 1.4126. Min Range: -1.4126

Max Act: 0.8671. Min Act: -0.0000

Data Index: 71410 (The Pile)

Max Activating Token Index: 1000

Text #15

Max Range: 1.4126. Min Range: -1.4126

Max Act: 0.8938. Min Act: -0.0000

Data Index: 42552 (The Pile)

Max Activating Token Index: 728

Text #16

Max Range: 1.4126. Min Range: -1.4126

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1459955 (The Pile)

Max Activating Token Index: 142

Text #17

Max Range: 1.4126. Min Range: -1.4126

Max Act: 0.8300. Min Act: -0.0000

Data Index: 228030 (The Pile)

Max Activating Token Index: 662

Text #18

Max Range: 1.4126. Min Range: -1.4126

Max Act: 0.8741. Min Act: -0.0000

Data Index: 60295 (The Pile)

Max Activating Token Index: 162

Text #19

Max Range: 1.4126. Min Range: -1.4126

Max Act: 0.8138. Min Act: -0.0000

Data Index: 541987 (The Pile)

Max Activating Token Index: 97