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

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

Neuron 5063 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.2221. Min Act: -0.0000

Data Index: 764686 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1822. Min Act: -0.0000

Data Index: 957127 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1167210 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1232802 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1633. Min Act: -0.0000

Data Index: 1136981 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1719. Min Act: -0.0000

Data Index: 235332 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1637. Min Act: -0.0000

Data Index: 504720 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1577. Min Act: -0.0000

Data Index: 164519 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1192699 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1613. Min Act: -0.0000

Data Index: 54458 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1631. Min Act: -0.0000

Data Index: 889854 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1357. Min Act: -0.0000

Data Index: 927471 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1124. Min Act: -0.0000

Data Index: 300743 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1366. Min Act: -0.0000

Data Index: 667747 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1097025 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1070. Min Act: -0.0000

Data Index: 1362552 (Python Code)

Max Activating Token Index: 391

Text #16

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1177185 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1401. Min Act: -0.0000

Data Index: 1125864 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1377. Min Act: -0.0000

Data Index: 1293192 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1183. Min Act: -0.0000

Data Index: 31557 (C4 (Web Text))

Max Activating Token Index: 383