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

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

Neuron 2157 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2669. Min Range: -3.2669

Max Act: 3.1553. Min Act: -0.0000

Data Index: 360308 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 3.2669. Min Range: -3.2669

Max Act: 3.2669. Min Act: -0.0000

Data Index: 1211868 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 3.2669. Min Range: -3.2669

Max Act: 3.1142. Min Act: -0.0000

Data Index: 762815 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 3.2669. Min Range: -3.2669

Max Act: 3.2633. Min Act: -0.0000

Data Index: 788000 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 3.2669. Min Range: -3.2669

Max Act: 3.1403. Min Act: -0.0000

Data Index: 1096471 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 3.2669. Min Range: -3.2669

Max Act: 3.1462. Min Act: -0.0000

Data Index: 413573 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 3.2669. Min Range: -3.2669

Max Act: 2.9962. Min Act: -0.0000

Data Index: 338205 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 3.2669. Min Range: -3.2669

Max Act: 2.9720. Min Act: -0.0000

Data Index: 38449 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 3.2669. Min Range: -3.2669

Max Act: 2.9916. Min Act: -0.0000

Data Index: 954050 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 3.2669. Min Range: -3.2669

Max Act: 3.1205. Min Act: -0.0000

Data Index: 116425 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 3.2669. Min Range: -3.2669

Max Act: 3.0749. Min Act: -0.0000

Data Index: 837225 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 3.2669. Min Range: -3.2669

Max Act: 3.0169. Min Act: -0.0000

Data Index: 1153994 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 3.2669. Min Range: -3.2669

Max Act: 3.0178. Min Act: -0.0000

Data Index: 794290 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 3.2669. Min Range: -3.2669

Max Act: 2.8626. Min Act: -0.0000

Data Index: 489141 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 3.2669. Min Range: -3.2669

Max Act: 3.0014. Min Act: -0.0000

Data Index: 1192089 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 3.2669. Min Range: -3.2669

Max Act: 2.9859. Min Act: -0.0000

Data Index: 1153847 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 3.2669. Min Range: -3.2669

Max Act: 2.8564. Min Act: -0.0000

Data Index: 516996 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 3.2669. Min Range: -3.2669

Max Act: 3.0138. Min Act: -0.0000

Data Index: 921493 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 3.2669. Min Range: -3.2669

Max Act: 2.9835. Min Act: -0.0000

Data Index: 334095 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 3.2669. Min Range: -3.2669

Max Act: 3.1432. Min Act: -0.0000

Data Index: 1197604 (C4 (Web Text))

Max Activating Token Index: 806