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

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

Neuron 4727 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1276. Min Act: -0.0000

Data Index: 958952 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1146. Min Act: -0.0001

Data Index: 1272078 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1199. Min Act: -0.0000

Data Index: 419516 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1183. Min Act: -0.0001

Data Index: 926238 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1074372 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1233712 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0956. Min Act: -0.0000

Data Index: 147169 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0950. Min Act: -0.0000

Data Index: 766932 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1052. Min Act: -0.0000

Data Index: 212643 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1061. Min Act: -0.0000

Data Index: 431160 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1097. Min Act: -0.0000

Data Index: 774017 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1541530 (Python Code)

Max Activating Token Index: 189

Text #12

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1043. Min Act: -0.0000

Data Index: 284108 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0984. Min Act: -0.0000

Data Index: 1178505 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0949. Min Act: -0.0000

Data Index: 157003 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1031059 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1278356 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0910. Min Act: -0.0000

Data Index: 587830 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0940. Min Act: -0.0000

Data Index: 381372 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0997. Min Act: -0.0000

Data Index: 357740 (C4 (Web Text))

Max Activating Token Index: 646