Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 904 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0786. Min Act: -0.0003

Data Index: 761653 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0834. Min Act: -0.0003

Data Index: 1251029 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0865. Min Act: -0.0003

Data Index: 1265638 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0743. Min Act: -0.0003

Data Index: 1085401 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0802. Min Act: -0.0003

Data Index: 40240 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0791. Min Act: -0.0004

Data Index: 667877 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0858. Min Act: -0.0003

Data Index: 886974 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0802. Min Act: -0.0003

Data Index: 891496 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0727. Min Act: -0.0003

Data Index: 134078 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0778. Min Act: -0.0003

Data Index: 91706 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0784. Min Act: -0.0003

Data Index: 1147305 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0752. Min Act: -0.0003

Data Index: 679579 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0791. Min Act: -0.0003

Data Index: 844583 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0753. Min Act: -0.0003

Data Index: 138083 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0780. Min Act: -0.0004

Data Index: 933171 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0785. Min Act: -0.0003

Data Index: 1085828 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0780. Min Act: -0.0003

Data Index: 794785 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0712. Min Act: -0.0003

Data Index: 1118187 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0697. Min Act: -0.0003

Data Index: 200287 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0750. Min Act: -0.0003

Data Index: 494988 (C4 (Web Text))

Max Activating Token Index: 958