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

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

Neuron 3617 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.2027. Min Act: -0.0000

Data Index: 954918 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1756. Min Act: -0.0000

Data Index: 256932 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1704. Min Act: -0.0000

Data Index: 296678 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1590. Min Act: -0.0000

Data Index: 1226976 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1628. Min Act: -0.0000

Data Index: 995359 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1546. Min Act: -0.0000

Data Index: 938589 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1574. Min Act: -0.0000

Data Index: 205896 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1346. Min Act: -0.0000

Data Index: 248226 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1410. Min Act: -0.0000

Data Index: 935366 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1268. Min Act: -0.0000

Data Index: 1334070 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1288. Min Act: -0.0000

Data Index: 149491 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1340. Min Act: -0.0000

Data Index: 410629 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1236. Min Act: 0.0000

Data Index: 125256 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1240. Min Act: -0.0000

Data Index: 290403 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1182. Min Act: -0.0000

Data Index: 1084439 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1255. Min Act: 0.0000

Data Index: 945325 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1194. Min Act: -0.0000

Data Index: 827810 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1220. Min Act: -0.0000

Data Index: 1075773 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1119. Min Act: -0.0000

Data Index: 79030 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1123. Min Act: -0.0000

Data Index: 977965 (C4 (Web Text))

Max Activating Token Index: 333