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

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

Neuron 5323 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: 1.2102. Min Range: -1.2102

Max Act: 1.2102. Min Act: -0.0000

Data Index: 1543376 (Python Code)

Max Activating Token Index: 916

Text #1

Max Range: 1.2102. Min Range: -1.2102

Max Act: 1.0032. Min Act: -0.0000

Data Index: 747284 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.9404. Min Act: -0.0000

Data Index: 691140 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.9000. Min Act: -0.0000

Data Index: 225250 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.8731. Min Act: -0.0000

Data Index: 1321711 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.8369. Min Act: -0.0000

Data Index: 1454241 (Python Code)

Max Activating Token Index: 461

Text #6

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.8469. Min Act: -0.0000

Data Index: 731754 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.8260. Min Act: -0.0000

Data Index: 1120430 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.8221. Min Act: -0.0000

Data Index: 236076 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.8143. Min Act: -0.0000

Data Index: 320586 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.8125. Min Act: -0.0000

Data Index: 449038 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.8072. Min Act: -0.0000

Data Index: 392598 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.7877. Min Act: -0.0000

Data Index: 951302 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.7742. Min Act: -0.0000

Data Index: 284326 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.7953. Min Act: -0.0000

Data Index: 781294 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.7586. Min Act: -0.0000

Data Index: 200813 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1543839 (Python Code)

Max Activating Token Index: 370

Text #17

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.7333. Min Act: 0.0000

Data Index: 1116404 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1651375 (Python Code)

Max Activating Token Index: 877

Text #19

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.7401. Min Act: -0.0000

Data Index: 1333867 (C4 (Web Text))

Max Activating Token Index: 683