Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 481 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1177. Min Act: -0.0001

Data Index: 1318878 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1194. Min Act: -0.0001

Data Index: 312022 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1095. Min Act: -0.0001

Data Index: 37175 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1033. Min Act: -0.0001

Data Index: 998360 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1044. Min Act: -0.0001

Data Index: 732877 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1083. Min Act: -0.0001

Data Index: 388068 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1042. Min Act: -0.0001

Data Index: 516352 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1023. Min Act: -0.0001

Data Index: 709682 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1116. Min Act: -0.0001

Data Index: 215666 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1036082 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0992. Min Act: -0.0001

Data Index: 602899 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0981. Min Act: -0.0001

Data Index: 347457 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1041. Min Act: -0.0001

Data Index: 1304508 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0956. Min Act: -0.0001

Data Index: 682922 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0962. Min Act: -0.0001

Data Index: 155718 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0970. Min Act: -0.0001

Data Index: 405180 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1617468 (Python Code)

Max Activating Token Index: 1016

Text #17

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0931. Min Act: -0.0001

Data Index: 788383 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0828. Min Act: -0.0001

Data Index: 205506 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1022268 (C4 (Web Text))

Max Activating Token Index: 851