Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1321 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0979. Min Act: -0.0001

Data Index: 1337797 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0863. Min Act: -0.0000

Data Index: 103200 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0883. Min Act: -0.0001

Data Index: 1208912 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0849. Min Act: -0.0001

Data Index: 272145 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0861. Min Act: -0.0001

Data Index: 475625 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1208175 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0808. Min Act: -0.0001

Data Index: 686489 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0805. Min Act: -0.0001

Data Index: 197723 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0828. Min Act: -0.0001

Data Index: 85269 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0858. Min Act: -0.0001

Data Index: 1317962 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0772. Min Act: -0.0001

Data Index: 1296439 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0786. Min Act: -0.0001

Data Index: 948284 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0716. Min Act: -0.0000

Data Index: 479986 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0777. Min Act: -0.0001

Data Index: 543607 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0767. Min Act: -0.0001

Data Index: 196160 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0745. Min Act: -0.0001

Data Index: 1105820 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0734. Min Act: -0.0000

Data Index: 645086 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0645. Min Act: -0.0001

Data Index: 1090553 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0837. Min Act: -0.0001

Data Index: 1107658 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0753. Min Act: -0.0001

Data Index: 343481 (C4 (Web Text))

Max Activating Token Index: 852