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

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

Neuron 736 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.8440. Min Range: -11.8440

Max Act: 11.8440. Min Act: -0.0000

Data Index: 1049518 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 11.8440. Min Range: -11.8440

Max Act: 11.1130. Min Act: -0.0000

Data Index: 965500 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 11.8440. Min Range: -11.8440

Max Act: 11.0598. Min Act: -0.0000

Data Index: 314984 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 11.8440. Min Range: -11.8440

Max Act: 10.9181. Min Act: -0.0000

Data Index: 789069 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 11.8440. Min Range: -11.8440

Max Act: 10.5411. Min Act: -0.0000

Data Index: 198463 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 11.8440. Min Range: -11.8440

Max Act: 10.7167. Min Act: -0.0000

Data Index: 552068 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 11.8440. Min Range: -11.8440

Max Act: 7.5079. Min Act: -0.0000

Data Index: 1241581 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 11.8440. Min Range: -11.8440

Max Act: 6.9926. Min Act: -0.0000

Data Index: 346553 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 11.8440. Min Range: -11.8440

Max Act: 6.7777. Min Act: 0.0000

Data Index: 223419 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 11.8440. Min Range: -11.8440

Max Act: 6.5860. Min Act: -0.0000

Data Index: 1243647 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 11.8440. Min Range: -11.8440

Max Act: 6.3074. Min Act: -0.0000

Data Index: 770593 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 11.8440. Min Range: -11.8440

Max Act: 5.8188. Min Act: -0.0000

Data Index: 465449 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 11.8440. Min Range: -11.8440

Max Act: 5.8438. Min Act: -0.0000

Data Index: 86855 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 11.8440. Min Range: -11.8440

Max Act: 5.9795. Min Act: -0.0000

Data Index: 555375 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 11.8440. Min Range: -11.8440

Max Act: 5.7163. Min Act: -0.0000

Data Index: 531720 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 11.8440. Min Range: -11.8440

Max Act: 5.7924. Min Act: -0.0000

Data Index: 31813 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 11.8440. Min Range: -11.8440

Max Act: 5.4459. Min Act: 0.0001

Data Index: 526646 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 11.8440. Min Range: -11.8440

Max Act: 5.4558. Min Act: -0.0000

Data Index: 63422 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 11.8440. Min Range: -11.8440

Max Act: 5.4224. Min Act: -0.0000

Data Index: 1331366 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 11.8440. Min Range: -11.8440

Max Act: 5.2982. Min Act: -0.0000

Data Index: 342486 (C4 (Web Text))

Max Activating Token Index: 347