Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5983 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1931. Min Range: -4.1931

Max Act: 4.1931. Min Act: -0.0000

Data Index: 698527 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 4.1931. Min Range: -4.1931

Max Act: 3.9364. Min Act: -0.0000

Data Index: 563845 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 4.1931. Min Range: -4.1931

Max Act: 3.8768. Min Act: -0.0000

Data Index: 935261 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 4.1931. Min Range: -4.1931

Max Act: 4.0087. Min Act: -0.0000

Data Index: 672675 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 4.1931. Min Range: -4.1931

Max Act: 3.8420. Min Act: -0.0000

Data Index: 1026228 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 4.1931. Min Range: -4.1931

Max Act: 3.8150. Min Act: -0.0000

Data Index: 1050670 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 4.1931. Min Range: -4.1931

Max Act: 3.8347. Min Act: -0.0000

Data Index: 567022 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 4.1931. Min Range: -4.1931

Max Act: 3.8028. Min Act: -0.0000

Data Index: 256831 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 4.1931. Min Range: -4.1931

Max Act: 3.6218. Min Act: -0.0000

Data Index: 576357 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 4.1931. Min Range: -4.1931

Max Act: 3.7295. Min Act: -0.0000

Data Index: 796762 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 4.1931. Min Range: -4.1931

Max Act: 3.9112. Min Act: -0.0000

Data Index: 680901 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 4.1931. Min Range: -4.1931

Max Act: 3.7016. Min Act: -0.0000

Data Index: 750779 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 4.1931. Min Range: -4.1931

Max Act: 3.3763. Min Act: -0.0000

Data Index: 933384 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 4.1931. Min Range: -4.1931

Max Act: 3.5291. Min Act: -0.0000

Data Index: 122585 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 4.1931. Min Range: -4.1931

Max Act: 3.8148. Min Act: -0.0000

Data Index: 1031909 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 4.1931. Min Range: -4.1931

Max Act: 3.6071. Min Act: -0.0000

Data Index: 1123338 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 4.1931. Min Range: -4.1931

Max Act: 3.6064. Min Act: -0.0000

Data Index: 979111 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 4.1931. Min Range: -4.1931

Max Act: 3.5739. Min Act: -0.0000

Data Index: 699514 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 4.1931. Min Range: -4.1931

Max Act: 3.5581. Min Act: -0.0000

Data Index: 1186798 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 4.1931. Min Range: -4.1931

Max Act: 3.5517. Min Act: -0.0000

Data Index: 1225099 (C4 (Web Text))

Max Activating Token Index: 475