Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2164 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1208348 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1138716 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1118463 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6939. Min Act: -0.0000

Data Index: 990611 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1159875 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6849. Min Act: -0.0000

Data Index: 521160 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6416. Min Act: -0.0000

Data Index: 269854 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6840. Min Act: -0.0000

Data Index: 735409 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6426. Min Act: -0.0000

Data Index: 599215 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6555. Min Act: -0.0000

Data Index: 250511 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1052276 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6303. Min Act: -0.0000

Data Index: 97492 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5729. Min Act: 0.0000

Data Index: 408022 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5825. Min Act: -0.0000

Data Index: 824440 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5589. Min Act: -0.0000

Data Index: 1083753 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5616. Min Act: -0.0000

Data Index: 198630 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1228707 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5735. Min Act: -0.0000

Data Index: 808572 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1134061 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5554. Min Act: -0.0000

Data Index: 96215 (C4 (Web Text))

Max Activating Token Index: 669