Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2441 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1992. Min Act: -0.0001

Data Index: 202661 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1126. Min Act: -0.0002

Data Index: 175368 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1097. Min Act: -0.0001

Data Index: 362998 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1043. Min Act: -0.0001

Data Index: 555503 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1031. Min Act: -0.0001

Data Index: 584986 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1025. Min Act: -0.0001

Data Index: 214625 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1004. Min Act: -0.0001

Data Index: 466212 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1046. Min Act: -0.0001

Data Index: 898605 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1021. Min Act: -0.0001

Data Index: 423562 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1023. Min Act: -0.0001

Data Index: 345013 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.0993. Min Act: -0.0001

Data Index: 923834 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1014. Min Act: -0.0001

Data Index: 551109 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.0978. Min Act: -0.0001

Data Index: 31672 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.0979. Min Act: -0.0001

Data Index: 271271 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.0987. Min Act: -0.0001

Data Index: 536725 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.0972. Min Act: -0.0001

Data Index: 929841 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.0968. Min Act: -0.0001

Data Index: 4991 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.0979. Min Act: -0.0001

Data Index: 696599 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1337233 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.0964. Min Act: -0.0001

Data Index: 520033 (C4 (Web Text))

Max Activating Token Index: 724