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

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

Neuron 2154 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.5588. Min Act: -0.0001

Data Index: 742190 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.5299. Min Act: -0.0000

Data Index: 1022523 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.5171. Min Act: -0.0000

Data Index: 535248 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.5039. Min Act: -0.0000

Data Index: 1284173 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.5000. Min Act: -0.0000

Data Index: 115089 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.4831. Min Act: -0.0000

Data Index: 659007 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.4649. Min Act: -0.0000

Data Index: 699831 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.4759. Min Act: -0.0000

Data Index: 1022748 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.4362. Min Act: -0.0001

Data Index: 148986 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.4622. Min Act: -0.0001

Data Index: 673409 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1348931 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.3987. Min Act: -0.0001

Data Index: 1074209 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.4447. Min Act: -0.0001

Data Index: 495782 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.3970. Min Act: -0.0000

Data Index: 254697 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1289842 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.4108. Min Act: -0.0000

Data Index: 769585 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.4240. Min Act: -0.0000

Data Index: 959229 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.4105. Min Act: -0.0001

Data Index: 439810 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.4041. Min Act: -0.0001

Data Index: 951673 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.5588. Min Range: -0.5588

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1298988 (C4 (Web Text))

Max Activating Token Index: 779