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

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

Neuron 3381 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3220. Min Range: -3.3220

Max Act: 3.3220. Min Act: -0.0000

Data Index: 1038688 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 3.3220. Min Range: -3.3220

Max Act: 2.2909. Min Act: -0.0000

Data Index: 15407 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 3.3220. Min Range: -3.3220

Max Act: 2.3191. Min Act: -0.0000

Data Index: 55205 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 3.3220. Min Range: -3.3220

Max Act: 2.4000. Min Act: -0.0000

Data Index: 651196 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 3.3220. Min Range: -3.3220

Max Act: 2.0659. Min Act: -0.0000

Data Index: 953564 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 3.3220. Min Range: -3.3220

Max Act: 1.7690. Min Act: -0.0000

Data Index: 1014962 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 3.3220. Min Range: -3.3220

Max Act: 1.5800. Min Act: -0.0000

Data Index: 797634 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 3.3220. Min Range: -3.3220

Max Act: 1.5932. Min Act: -0.0000

Data Index: 1361410 (Python Code)

Max Activating Token Index: 504

Text #8

Max Range: 3.3220. Min Range: -3.3220

Max Act: 1.5151. Min Act: -0.0000

Data Index: 756843 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 3.3220. Min Range: -3.3220

Max Act: 1.5633. Min Act: -0.0000

Data Index: 690206 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 3.3220. Min Range: -3.3220

Max Act: 1.5590. Min Act: -0.0000

Data Index: 1178507 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 3.3220. Min Range: -3.3220

Max Act: 1.6438. Min Act: -0.0000

Data Index: 863848 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 3.3220. Min Range: -3.3220

Max Act: 1.4174. Min Act: -0.0000

Data Index: 1555773 (Python Code)

Max Activating Token Index: 772

Text #13

Max Range: 3.3220. Min Range: -3.3220

Max Act: 1.4992. Min Act: -0.0000

Data Index: 1644231 (Python Code)

Max Activating Token Index: 363

Text #14

Max Range: 3.3220. Min Range: -3.3220

Max Act: 1.4027. Min Act: -0.0000

Data Index: 1407666 (Python Code)

Max Activating Token Index: 439

Text #15

Max Range: 3.3220. Min Range: -3.3220

Max Act: 1.5691. Min Act: -0.0000

Data Index: 1077704 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 3.3220. Min Range: -3.3220

Max Act: 1.4152. Min Act: -0.0000

Data Index: 462943 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 3.3220. Min Range: -3.3220

Max Act: 1.4863. Min Act: -0.0000

Data Index: 1188057 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 3.3220. Min Range: -3.3220

Max Act: 1.2313. Min Act: -0.0000

Data Index: 1255191 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 3.3220. Min Range: -3.3220

Max Act: 1.4749. Min Act: -0.0000

Data Index: 1571361 (Python Code)

Max Activating Token Index: 431