Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1336 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1293. Min Act: -0.0002

Data Index: 606355 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1253. Min Act: -0.0002

Data Index: 936500 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1154. Min Act: -0.0002

Data Index: 164454 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1197. Min Act: -0.0002

Data Index: 392825 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1234. Min Act: -0.0002

Data Index: 626514 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1110. Min Act: -0.0002

Data Index: 1330913 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1052. Min Act: -0.0002

Data Index: 1333817 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1030. Min Act: -0.0002

Data Index: 1052479 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1073. Min Act: -0.0002

Data Index: 894124 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0991. Min Act: -0.0002

Data Index: 271454 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1019. Min Act: -0.0002

Data Index: 78556 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0952. Min Act: -0.0002

Data Index: 698720 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0976. Min Act: -0.0002

Data Index: 186982 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0949. Min Act: -0.0002

Data Index: 1309023 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0945. Min Act: -0.0002

Data Index: 421790 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0917. Min Act: -0.0002

Data Index: 737285 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0908. Min Act: -0.0002

Data Index: 1021338 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0902. Min Act: -0.0002

Data Index: 185464 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0922. Min Act: -0.0002

Data Index: 1228724 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0874. Min Act: -0.0002

Data Index: 31420 (C4 (Web Text))

Max Activating Token Index: 1005