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

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

Neuron 816 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1158. Min Act: -0.0003

Data Index: 1357654 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0982. Min Act: -0.0003

Data Index: 845500 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1029. Min Act: -0.0003

Data Index: 577083 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0892. Min Act: -0.0003

Data Index: 748649 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0861. Min Act: -0.0003

Data Index: 930437 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0924. Min Act: -0.0003

Data Index: 319093 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0848. Min Act: -0.0003

Data Index: 261400 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0908. Min Act: -0.0003

Data Index: 267133 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0795. Min Act: -0.0003

Data Index: 764589 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0666. Min Act: -0.0003

Data Index: 695132 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0763. Min Act: -0.0003

Data Index: 79348 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0818. Min Act: -0.0003

Data Index: 983356 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0802. Min Act: -0.0003

Data Index: 415297 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0771. Min Act: -0.0003

Data Index: 988196 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0764. Min Act: -0.0003

Data Index: 679969 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0820. Min Act: -0.0003

Data Index: 248375 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0821. Min Act: -0.0003

Data Index: 393072 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0762. Min Act: -0.0003

Data Index: 1078011 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0676. Min Act: -0.0003

Data Index: 568999 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0748. Min Act: -0.0003

Data Index: 1342047 (C4 (Web Text))

Max Activating Token Index: 837