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

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

Neuron 1044 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.4850. Min Act: -0.0001

Data Index: 1074814 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.3540. Min Act: -0.0001

Data Index: 553638 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.3141. Min Act: -0.0001

Data Index: 745361 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.3146. Min Act: -0.0002

Data Index: 960519 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.2317. Min Act: -0.0002

Data Index: 431149 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.3829. Min Act: -0.0002

Data Index: 522252 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.2166. Min Act: -0.0001

Data Index: 1054108 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1885. Min Act: -0.0002

Data Index: 1268010 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1935. Min Act: -0.0001

Data Index: 124382 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.2160. Min Act: -0.0001

Data Index: 254497 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1745. Min Act: -0.0001

Data Index: 361590 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1419. Min Act: -0.0001

Data Index: 232464 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1080. Min Act: -0.0002

Data Index: 320048 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.0670. Min Act: -0.0002

Data Index: 116505 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1535. Min Act: -0.0001

Data Index: 700025 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.0631. Min Act: -0.0001

Data Index: 1345252 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.0598. Min Act: -0.0002

Data Index: 1276840 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1500. Min Act: -0.0001

Data Index: 615517 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1182. Min Act: -0.0001

Data Index: 608787 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1147. Min Act: -0.0002

Data Index: 432553 (C4 (Web Text))

Max Activating Token Index: 473