Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4940 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2356. Min Act: -0.0002

Data Index: 1494940 (Python Code)

Max Activating Token Index: 183

Text #1

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2355. Min Act: -0.0002

Data Index: 1645234 (Python Code)

Max Activating Token Index: 126

Text #2

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2171. Min Act: -0.0002

Data Index: 1623625 (Python Code)

Max Activating Token Index: 121

Text #3

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2144. Min Act: -0.0002

Data Index: 1488669 (Python Code)

Max Activating Token Index: 788

Text #4

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2114. Min Act: -0.0002

Data Index: 1407540 (Python Code)

Max Activating Token Index: 680

Text #5

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2134. Min Act: -0.0002

Data Index: 1477352 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2064. Min Act: -0.0002

Data Index: 1384404 (Python Code)

Max Activating Token Index: 229

Text #7

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.1989. Min Act: -0.0002

Data Index: 1502980 (Python Code)

Max Activating Token Index: 79

Text #8

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2097. Min Act: -0.0002

Data Index: 1507223 (Python Code)

Max Activating Token Index: 405

Text #9

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2091. Min Act: -0.0002

Data Index: 1410323 (Python Code)

Max Activating Token Index: 418

Text #10

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2255. Min Act: -0.0002

Data Index: 1621427 (Python Code)

Max Activating Token Index: 866

Text #11

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2021. Min Act: -0.0002

Data Index: 1545724 (Python Code)

Max Activating Token Index: 203

Text #12

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2147. Min Act: -0.0002

Data Index: 1508055 (Python Code)

Max Activating Token Index: 367

Text #13

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2162. Min Act: -0.0002

Data Index: 1504857 (Python Code)

Max Activating Token Index: 552

Text #14

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2133. Min Act: -0.0002

Data Index: 1606558 (Python Code)

Max Activating Token Index: 118

Text #15

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2036. Min Act: -0.0002

Data Index: 1497301 (Python Code)

Max Activating Token Index: 370

Text #16

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.1974. Min Act: -0.0002

Data Index: 1405536 (Python Code)

Max Activating Token Index: 638

Text #17

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2192. Min Act: -0.0002

Data Index: 1402364 (Python Code)

Max Activating Token Index: 282

Text #18

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2051. Min Act: -0.0002

Data Index: 1526672 (Python Code)

Max Activating Token Index: 567

Text #19

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2150. Min Act: -0.0002

Data Index: 1504125 (Python Code)

Max Activating Token Index: 997