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

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

Neuron 3881 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.3085. Min Act: -0.0001

Data Index: 790792 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.2393. Min Act: -0.0001

Data Index: 1227719 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1261646 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.2187. Min Act: -0.0000

Data Index: 767783 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.2141. Min Act: -0.0000

Data Index: 90669 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.2210. Min Act: -0.0000

Data Index: 193986 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.2047. Min Act: -0.0001

Data Index: 404311 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.2040. Min Act: -0.0001

Data Index: 1148889 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1871. Min Act: -0.0000

Data Index: 697662 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1989. Min Act: -0.0000

Data Index: 380551 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1874. Min Act: -0.0001

Data Index: 690008 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1851. Min Act: -0.0000

Data Index: 767886 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1870. Min Act: -0.0000

Data Index: 410186 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1849. Min Act: -0.0000

Data Index: 183820 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1858. Min Act: -0.0000

Data Index: 137866 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1851. Min Act: -0.0001

Data Index: 347042 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1982. Min Act: -0.0000

Data Index: 731085 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1833. Min Act: -0.0000

Data Index: 711170 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1814. Min Act: -0.0000

Data Index: 164994 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1894. Min Act: -0.0000

Data Index: 675402 (C4 (Web Text))

Max Activating Token Index: 720