Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1936 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1301. Min Act: -0.0003

Data Index: 1622393 (Python Code)

Max Activating Token Index: 178

Text #1

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1207. Min Act: -0.0002

Data Index: 1469386 (Python Code)

Max Activating Token Index: 393

Text #2

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1202. Min Act: -0.0003

Data Index: 1644556 (Python Code)

Max Activating Token Index: 243

Text #3

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1123. Min Act: -0.0003

Data Index: 1502569 (Python Code)

Max Activating Token Index: 510

Text #4

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1078. Min Act: -0.0003

Data Index: 1391769 (Python Code)

Max Activating Token Index: 290

Text #5

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1058. Min Act: -0.0003

Data Index: 1550157 (Python Code)

Max Activating Token Index: 865

Text #6

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1119. Min Act: -0.0003

Data Index: 1574820 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1080. Min Act: -0.0004

Data Index: 1459351 (Python Code)

Max Activating Token Index: 420

Text #8

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1079. Min Act: -0.0003

Data Index: 1472887 (Python Code)

Max Activating Token Index: 453

Text #9

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1029. Min Act: -0.0002

Data Index: 1382958 (Python Code)

Max Activating Token Index: 235

Text #10

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1058. Min Act: -0.0004

Data Index: 1562709 (Python Code)

Max Activating Token Index: 835

Text #11

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1062. Min Act: -0.0003

Data Index: 1362881 (Python Code)

Max Activating Token Index: 85

Text #12

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1120. Min Act: -0.0003

Data Index: 1468975 (Python Code)

Max Activating Token Index: 487

Text #13

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1002. Min Act: -0.0003

Data Index: 1444638 (Python Code)

Max Activating Token Index: 413

Text #14

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1087. Min Act: -0.0003

Data Index: 1631683 (Python Code)

Max Activating Token Index: 540

Text #15

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1084. Min Act: -0.0002

Data Index: 1540892 (Python Code)

Max Activating Token Index: 389

Text #16

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1026. Min Act: -0.0003

Data Index: 1630281 (Python Code)

Max Activating Token Index: 216

Text #17

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1008. Min Act: -0.0003

Data Index: 1479284 (Python Code)

Max Activating Token Index: 498

Text #18

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1052. Min Act: -0.0004

Data Index: 1400125 (Python Code)

Max Activating Token Index: 175

Text #19

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0992. Min Act: -0.0003

Data Index: 1589652 (Python Code)

Max Activating Token Index: 459