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

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

Neuron 2530 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2194. Min Act: -0.0000

Data Index: 323824 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2162. Min Act: -0.0000

Data Index: 154735 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1964. Min Act: -0.0000

Data Index: 613731 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1910. Min Act: -0.0000

Data Index: 838589 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1955. Min Act: -0.0000

Data Index: 346245 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1962. Min Act: -0.0000

Data Index: 13430 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1784. Min Act: -0.0001

Data Index: 809583 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1072747 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1914. Min Act: -0.0000

Data Index: 878561 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1783. Min Act: -0.0000

Data Index: 701781 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1258100 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1744. Min Act: -0.0001

Data Index: 1274977 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1731. Min Act: -0.0000

Data Index: 1068579 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1675. Min Act: -0.0001

Data Index: 1176654 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1646. Min Act: -0.0000

Data Index: 1126081 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1028841 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1598. Min Act: -0.0000

Data Index: 126275 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1593. Min Act: -0.0000

Data Index: 451972 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1588. Min Act: -0.0001

Data Index: 884246 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1645. Min Act: -0.0000

Data Index: 1561360 (Python Code)

Max Activating Token Index: 1007