Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 838 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2482. Min Act: -0.0001

Data Index: 1648193 (Python Code)

Max Activating Token Index: 856

Text #1

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2659. Min Act: -0.0001

Data Index: 1434792 (Python Code)

Max Activating Token Index: 658

Text #2

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2679. Min Act: -0.0001

Data Index: 1589083 (Python Code)

Max Activating Token Index: 839

Text #3

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2346. Min Act: -0.0001

Data Index: 1581015 (Python Code)

Max Activating Token Index: 105

Text #4

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2534. Min Act: -0.0001

Data Index: 1593314 (Python Code)

Max Activating Token Index: 705

Text #5

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2346. Min Act: -0.0001

Data Index: 1407630 (Python Code)

Max Activating Token Index: 774

Text #6

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2373. Min Act: -0.0001

Data Index: 1365415 (Python Code)

Max Activating Token Index: 110

Text #7

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2344. Min Act: -0.0001

Data Index: 149252 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2817. Min Act: -0.0001

Data Index: 1390227 (Python Code)

Max Activating Token Index: 858

Text #9

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2291. Min Act: -0.0001

Data Index: 1483925 (Python Code)

Max Activating Token Index: 304

Text #10

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2305. Min Act: -0.0001

Data Index: 1511078 (Python Code)

Max Activating Token Index: 97

Text #11

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2167. Min Act: -0.0001

Data Index: 1520856 (Python Code)

Max Activating Token Index: 160

Text #12

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2284. Min Act: -0.0001

Data Index: 1411374 (Python Code)

Max Activating Token Index: 312

Text #13

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2390. Min Act: -0.0001

Data Index: 1553706 (Python Code)

Max Activating Token Index: 139

Text #14

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2200. Min Act: -0.0001

Data Index: 1612911 (Python Code)

Max Activating Token Index: 133

Text #15

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2271. Min Act: -0.0001

Data Index: 1614016 (Python Code)

Max Activating Token Index: 705

Text #16

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2188. Min Act: -0.0001

Data Index: 1518374 (Python Code)

Max Activating Token Index: 164

Text #17

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2110. Min Act: -0.0001

Data Index: 1485336 (Python Code)

Max Activating Token Index: 167

Text #18

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2010. Min Act: -0.0001

Data Index: 1042580 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2055. Min Act: -0.0001

Data Index: 1521727 (Python Code)

Max Activating Token Index: 138