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

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

Neuron 5844 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.7245. Min Act: -0.0002

Data Index: 1278088 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6940. Min Act: -0.0002

Data Index: 1015711 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6785. Min Act: -0.0002

Data Index: 1317761 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6757. Min Act: -0.0002

Data Index: 999982 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6507. Min Act: -0.0002

Data Index: 90340 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6515. Min Act: -0.0002

Data Index: 1262998 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6691. Min Act: -0.0002

Data Index: 853840 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6397. Min Act: -0.0002

Data Index: 903169 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6286. Min Act: -0.0002

Data Index: 899400 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6370. Min Act: -0.0002

Data Index: 465175 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6094. Min Act: -0.0002

Data Index: 191132 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6247. Min Act: -0.0002

Data Index: 336886 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6249. Min Act: -0.0002

Data Index: 134147 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6452. Min Act: -0.0002

Data Index: 624735 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6133. Min Act: -0.0002

Data Index: 599781 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5921. Min Act: -0.0002

Data Index: 842673 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6327. Min Act: -0.0002

Data Index: 18283 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6125. Min Act: -0.0002

Data Index: 205264 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5784. Min Act: -0.0002

Data Index: 1256300 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5977. Min Act: -0.0002

Data Index: 474260 (C4 (Web Text))

Max Activating Token Index: 556