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

Dataset: The Pile

Neuron 923 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0455. Min Range: -1.0455

Max Act: 0.9883. Min Act: -0.0000

Data Index: 444212 (The Pile)

Max Activating Token Index: 352

Text #1

Max Range: 1.0455. Min Range: -1.0455

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1179315 (The Pile)

Max Activating Token Index: 639

Text #2

Max Range: 1.0455. Min Range: -1.0455

Max Act: 1.0455. Min Act: -0.0000

Data Index: 1071642 (The Pile)

Max Activating Token Index: 939

Text #3

Max Range: 1.0455. Min Range: -1.0455

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1525650 (The Pile)

Max Activating Token Index: 727

Text #4

Max Range: 1.0455. Min Range: -1.0455

Max Act: 1.0331. Min Act: -0.0000

Data Index: 1962377 (The Pile)

Max Activating Token Index: 157

Text #5

Max Range: 1.0455. Min Range: -1.0455

Max Act: 0.9294. Min Act: -0.0000

Data Index: 632755 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 1.0455. Min Range: -1.0455

Max Act: 0.9685. Min Act: -0.0000

Data Index: 147738 (The Pile)

Max Activating Token Index: 165

Text #7

Max Range: 1.0455. Min Range: -1.0455

Max Act: 0.9535. Min Act: -0.0000

Data Index: 846135 (The Pile)

Max Activating Token Index: 222

Text #8

Max Range: 1.0455. Min Range: -1.0455

Max Act: 0.9093. Min Act: -0.0000

Data Index: 852373 (The Pile)

Max Activating Token Index: 725

Text #9

Max Range: 1.0455. Min Range: -1.0455

Max Act: 0.9655. Min Act: -0.0000

Data Index: 576811 (The Pile)

Max Activating Token Index: 393

Text #10

Max Range: 1.0455. Min Range: -1.0455

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1891008 (The Pile)

Max Activating Token Index: 107

Text #11

Max Range: 1.0455. Min Range: -1.0455

Max Act: 0.8755. Min Act: -0.0000

Data Index: 136032 (The Pile)

Max Activating Token Index: 212

Text #12

Max Range: 1.0455. Min Range: -1.0455

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1815773 (The Pile)

Max Activating Token Index: 323

Text #13

Max Range: 1.0455. Min Range: -1.0455

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1523531 (The Pile)

Max Activating Token Index: 445

Text #14

Max Range: 1.0455. Min Range: -1.0455

Max Act: 0.8573. Min Act: -0.0000

Data Index: 936456 (The Pile)

Max Activating Token Index: 231

Text #15

Max Range: 1.0455. Min Range: -1.0455

Max Act: 0.8714. Min Act: -0.0000

Data Index: 628881 (The Pile)

Max Activating Token Index: 640

Text #16

Max Range: 1.0455. Min Range: -1.0455

Max Act: 0.8743. Min Act: -0.0000

Data Index: 798386 (The Pile)

Max Activating Token Index: 169

Text #17

Max Range: 1.0455. Min Range: -1.0455

Max Act: 0.9556. Min Act: -0.0000

Data Index: 1812824 (The Pile)

Max Activating Token Index: 791

Text #18

Max Range: 1.0455. Min Range: -1.0455

Max Act: 0.8454. Min Act: -0.0000

Data Index: 1519676 (The Pile)

Max Activating Token Index: 593

Text #19

Max Range: 1.0455. Min Range: -1.0455

Max Act: 0.8182. Min Act: -0.0000

Data Index: 300343 (The Pile)

Max Activating Token Index: 633