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

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

Neuron 3905 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.5023. Min Act: -0.0000

Data Index: 440438 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1610912 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1434802 (Python Code)

Max Activating Token Index: 17

Text #3

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4722. Min Act: -0.0000

Data Index: 1443524 (Python Code)

Max Activating Token Index: 827

Text #4

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1508558 (Python Code)

Max Activating Token Index: 829

Text #5

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1598602 (Python Code)

Max Activating Token Index: 470

Text #6

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4527. Min Act: -0.0000

Data Index: 1629183 (Python Code)

Max Activating Token Index: 773

Text #7

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4239. Min Act: -0.0000

Data Index: 1511287 (Python Code)

Max Activating Token Index: 709

Text #8

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1556999 (Python Code)

Max Activating Token Index: 646

Text #9

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4235. Min Act: 0.0000

Data Index: 1459365 (Python Code)

Max Activating Token Index: 399

Text #10

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4443. Min Act: -0.0000

Data Index: 1564146 (Python Code)

Max Activating Token Index: 693

Text #11

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4268. Min Act: -0.0000

Data Index: 834696 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1633119 (Python Code)

Max Activating Token Index: 935

Text #13

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4415. Min Act: -0.0000

Data Index: 671458 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1471375 (Python Code)

Max Activating Token Index: 750

Text #15

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1570599 (Python Code)

Max Activating Token Index: 588

Text #16

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4174. Min Act: -0.0000

Data Index: 815201 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1297238 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1290207 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4093. Min Act: -0.0000

Data Index: 317732 (C4 (Web Text))

Max Activating Token Index: 37