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

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

Neuron 1119 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: 1.6714. Min Range: -1.6714

Max Act: 1.6714. Min Act: -0.0002

Data Index: 207549 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.2991. Min Act: -0.0002

Data Index: 332142 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.2635. Min Act: -0.0002

Data Index: 236266 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.3144. Min Act: -0.0002

Data Index: 1207686 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.2743. Min Act: -0.0002

Data Index: 497047 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.1852. Min Act: -0.0002

Data Index: 157336 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.1828. Min Act: -0.0002

Data Index: 127 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.1735. Min Act: -0.0002

Data Index: 546123 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.2149. Min Act: -0.0002

Data Index: 292446 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.2360. Min Act: -0.0002

Data Index: 168942 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.2169. Min Act: -0.0002

Data Index: 800291 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.1989. Min Act: -0.0002

Data Index: 307543 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.1642. Min Act: -0.0002

Data Index: 570222 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.1522. Min Act: -0.0002

Data Index: 387870 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.1240. Min Act: -0.0002

Data Index: 453602 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.1271. Min Act: -0.0002

Data Index: 974762 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.1239. Min Act: -0.0002

Data Index: 147067 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.1554. Min Act: -0.0002

Data Index: 486975 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.1304. Min Act: -0.0002

Data Index: 1277483 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.1253. Min Act: -0.0002

Data Index: 1195552 (C4 (Web Text))

Max Activating Token Index: 20