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

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

Neuron 2421 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1140. Min Act: -0.0002

Data Index: 734193 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1053. Min Act: -0.0002

Data Index: 26535 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0960. Min Act: -0.0002

Data Index: 981949 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0994. Min Act: -0.0002

Data Index: 273261 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0898. Min Act: -0.0002

Data Index: 97880 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0836. Min Act: -0.0002

Data Index: 993860 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0827. Min Act: -0.0002

Data Index: 948852 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0819. Min Act: -0.0002

Data Index: 973964 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0832. Min Act: -0.0002

Data Index: 136684 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1341217 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1112802 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0736. Min Act: -0.0002

Data Index: 41760 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0699. Min Act: -0.0002

Data Index: 392669 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0677. Min Act: -0.0002

Data Index: 876921 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0717. Min Act: -0.0002

Data Index: 556925 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0696. Min Act: -0.0002

Data Index: 936493 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0707. Min Act: -0.0002

Data Index: 79038 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0737. Min Act: -0.0002

Data Index: 486595 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0703. Min Act: -0.0002

Data Index: 167433 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1067393 (C4 (Web Text))

Max Activating Token Index: 569