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

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

Neuron 1656 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.5691. Min Act: -0.0000

Data Index: 1259683 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.4604. Min Act: -0.0000

Data Index: 424812 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.4211. Min Act: -0.0000

Data Index: 1003157 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.4827. Min Act: -0.0000

Data Index: 120981 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.2861. Min Act: -0.0000

Data Index: 823333 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.2458. Min Act: -0.0000

Data Index: 1049435 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.2294. Min Act: -0.0000

Data Index: 121079 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.2383. Min Act: -0.0000

Data Index: 145005 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.2331. Min Act: -0.0000

Data Index: 763002 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.2598. Min Act: -0.0000

Data Index: 755000 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.2387. Min Act: -0.0000

Data Index: 1220222 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.1500. Min Act: -0.0000

Data Index: 553139 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.1313. Min Act: -0.0000

Data Index: 39772 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.1204. Min Act: -0.0000

Data Index: 658542 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.1927. Min Act: -0.0000

Data Index: 150201 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.1364. Min Act: -0.0000

Data Index: 488813 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.1688. Min Act: -0.0000

Data Index: 1183705 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.1062. Min Act: -0.0000

Data Index: 796186 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.1026. Min Act: -0.0000

Data Index: 1322678 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 1.5691. Min Range: -1.5691

Max Act: 1.0834. Min Act: -0.0000

Data Index: 479815 (C4 (Web Text))

Max Activating Token Index: 838