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

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

Neuron 713 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4771. Min Range: -3.4771

Max Act: 3.0406. Min Act: -0.0001

Data Index: 528124 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 3.4771. Min Range: -3.4771

Max Act: 3.4771. Min Act: -0.0001

Data Index: 1232426 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 3.4771. Min Range: -3.4771

Max Act: 3.2991. Min Act: -0.0001

Data Index: 150137 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 3.4771. Min Range: -3.4771

Max Act: 2.9101. Min Act: -0.0001

Data Index: 514015 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 3.4771. Min Range: -3.4771

Max Act: 2.7563. Min Act: -0.0001

Data Index: 315625 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 3.4771. Min Range: -3.4771

Max Act: 3.1585. Min Act: -0.0001

Data Index: 537376 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 3.4771. Min Range: -3.4771

Max Act: 2.7055. Min Act: -0.0001

Data Index: 1315939 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 3.4771. Min Range: -3.4771

Max Act: 2.4222. Min Act: -0.0001

Data Index: 840628 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 3.4771. Min Range: -3.4771

Max Act: 2.5782. Min Act: -0.0001

Data Index: 520615 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 3.4771. Min Range: -3.4771

Max Act: 2.5417. Min Act: -0.0001

Data Index: 207511 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 3.4771. Min Range: -3.4771

Max Act: 2.6822. Min Act: -0.0001

Data Index: 924580 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 3.4771. Min Range: -3.4771

Max Act: 2.1496. Min Act: -0.0001

Data Index: 777873 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 3.4771. Min Range: -3.4771

Max Act: 2.0990. Min Act: -0.0001

Data Index: 1277134 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 3.4771. Min Range: -3.4771

Max Act: 2.1927. Min Act: -0.0001

Data Index: 980558 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 3.4771. Min Range: -3.4771

Max Act: 2.0195. Min Act: -0.0001

Data Index: 75949 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 3.4771. Min Range: -3.4771

Max Act: 2.1727. Min Act: -0.0001

Data Index: 179899 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 3.4771. Min Range: -3.4771

Max Act: 2.2375. Min Act: -0.0001

Data Index: 987736 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 3.4771. Min Range: -3.4771

Max Act: 2.0323. Min Act: -0.0001

Data Index: 1116362 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 3.4771. Min Range: -3.4771

Max Act: 2.0205. Min Act: -0.0001

Data Index: 852797 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 3.4771. Min Range: -3.4771

Max Act: 2.0133. Min Act: -0.0001

Data Index: 812834 (C4 (Web Text))

Max Activating Token Index: 119