Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 896 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2456. Min Act: 0.0002

Data Index: 1571847 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2185. Min Act: -0.0000

Data Index: 1398958 (Python Code)

Max Activating Token Index: 243

Text #2

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2254. Min Act: 0.0000

Data Index: 1611004 (Python Code)

Max Activating Token Index: 82

Text #3

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1444065 (Python Code)

Max Activating Token Index: 637

Text #4

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1495811 (Python Code)

Max Activating Token Index: 174

Text #5

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2165. Min Act: 0.0000

Data Index: 1547217 (Python Code)

Max Activating Token Index: 113

Text #6

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2163. Min Act: 0.0001

Data Index: 1444825 (Python Code)

Max Activating Token Index: 389

Text #7

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2089. Min Act: -0.0001

Data Index: 1401502 (Python Code)

Max Activating Token Index: 194

Text #8

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2145. Min Act: 0.0002

Data Index: 1475614 (Python Code)

Max Activating Token Index: 94

Text #9

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2087. Min Act: 0.0002

Data Index: 1411850 (Python Code)

Max Activating Token Index: 116

Text #10

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2145. Min Act: 0.0002

Data Index: 1576400 (Python Code)

Max Activating Token Index: 771

Text #11

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2051. Min Act: 0.0002

Data Index: 1494836 (Python Code)

Max Activating Token Index: 450

Text #12

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2061. Min Act: 0.0000

Data Index: 1513615 (Python Code)

Max Activating Token Index: 517

Text #13

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2058. Min Act: 0.0002

Data Index: 1597522 (Python Code)

Max Activating Token Index: 378

Text #14

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2036. Min Act: 0.0002

Data Index: 1643663 (Python Code)

Max Activating Token Index: 617

Text #15

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2008. Min Act: -0.0001

Data Index: 1382867 (Python Code)

Max Activating Token Index: 59

Text #16

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1622109 (Python Code)

Max Activating Token Index: 95

Text #17

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2001. Min Act: 0.0002

Data Index: 1605070 (Python Code)

Max Activating Token Index: 855

Text #18

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1939. Min Act: 0.0001

Data Index: 1533414 (Python Code)

Max Activating Token Index: 235

Text #19

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1981. Min Act: 0.0002

Data Index: 1495076 (Python Code)

Max Activating Token Index: 968