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

Dataset: The Pile

Neuron 912 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: 0.1623. Min Range: -0.1623

Max Act: 0.1623. Min Act: -0.0000

Data Index: 643213 (The Pile)

Max Activating Token Index: 810

Text #1

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1527. Min Act: -0.0000

Data Index: 548236 (The Pile)

Max Activating Token Index: 773

Text #2

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1481594 (The Pile)

Max Activating Token Index: 912

Text #3

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1344. Min Act: -0.0000

Data Index: 1480306 (The Pile)

Max Activating Token Index: 58

Text #4

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1098. Min Act: -0.0000

Data Index: 658759 (The Pile)

Max Activating Token Index: 837

Text #5

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1332. Min Act: -0.0000

Data Index: 253032 (The Pile)

Max Activating Token Index: 705

Text #6

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1232. Min Act: -0.0000

Data Index: 373842 (The Pile)

Max Activating Token Index: 833

Text #7

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1152. Min Act: 0.0000

Data Index: 1772060 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1118. Min Act: -0.0000

Data Index: 245749 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1092. Min Act: -0.0000

Data Index: 642929 (The Pile)

Max Activating Token Index: 93

Text #10

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1134. Min Act: -0.0000

Data Index: 274712 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1162. Min Act: 0.0000

Data Index: 1003198 (The Pile)

Max Activating Token Index: 846

Text #12

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1123. Min Act: -0.0000

Data Index: 1216110 (The Pile)

Max Activating Token Index: 820

Text #13

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0959. Min Act: -0.0000

Data Index: 176321 (The Pile)

Max Activating Token Index: 145

Text #14

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0943. Min Act: -0.0000

Data Index: 257283 (The Pile)

Max Activating Token Index: 313

Text #15

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0933. Min Act: -0.0000

Data Index: 115019 (The Pile)

Max Activating Token Index: 727

Text #16

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1035. Min Act: -0.0000

Data Index: 473302 (The Pile)

Max Activating Token Index: 482

Text #17

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1182772 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1041. Min Act: -0.0000

Data Index: 323096 (The Pile)

Max Activating Token Index: 265

Text #19

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0956. Min Act: -0.0000

Data Index: 1668688 (The Pile)

Max Activating Token Index: 24