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

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

Neuron 1062 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.9149. Min Act: -0.0003

Data Index: 222824 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.9146. Min Act: -0.0002

Data Index: 1213593 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.8613. Min Act: -0.0002

Data Index: 134423 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7280. Min Act: -0.0002

Data Index: 805187 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7224. Min Act: -0.0002

Data Index: 1155549 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7484. Min Act: -0.0002

Data Index: 926916 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7493. Min Act: -0.0002

Data Index: 268134 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.6885. Min Act: -0.0002

Data Index: 786184 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7457. Min Act: -0.0002

Data Index: 610061 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7826. Min Act: -0.0002

Data Index: 970598 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7526. Min Act: -0.0002

Data Index: 1287623 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7053. Min Act: -0.0003

Data Index: 1271641 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.6573. Min Act: -0.0002

Data Index: 346845 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.6512. Min Act: -0.0002

Data Index: 165098 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.6372. Min Act: -0.0002

Data Index: 1158719 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.6198. Min Act: -0.0002

Data Index: 274890 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.6390. Min Act: -0.0002

Data Index: 273793 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.6115. Min Act: -0.0002

Data Index: 657941 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.6039. Min Act: -0.0002

Data Index: 178562 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.5968. Min Act: -0.0002

Data Index: 400453 (C4 (Web Text))

Max Activating Token Index: 562