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

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

Neuron 165 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.7531. Min Act: -0.0001

Data Index: 1148743 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.7076. Min Act: -0.0001

Data Index: 634279 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.5699. Min Act: -0.0001

Data Index: 371001 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.5171. Min Act: -0.0001

Data Index: 771683 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.4694. Min Act: -0.0000

Data Index: 308116 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.4482. Min Act: -0.0001

Data Index: 390876 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1059794 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.4007. Min Act: -0.0001

Data Index: 719701 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.4261. Min Act: -0.0001

Data Index: 569143 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.4062. Min Act: -0.0001

Data Index: 107967 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.4069. Min Act: -0.0000

Data Index: 396575 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.4214. Min Act: -0.0001

Data Index: 196023 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.4004. Min Act: -0.0001

Data Index: 505792 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.4370. Min Act: -0.0001

Data Index: 722933 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.4086. Min Act: -0.0000

Data Index: 883132 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.4494. Min Act: -0.0001

Data Index: 1088221 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.3877. Min Act: -0.0001

Data Index: 470509 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.4004. Min Act: -0.0001

Data Index: 1194140 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.3810. Min Act: -0.0001

Data Index: 1028722 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.4013. Min Act: -0.0001

Data Index: 748891 (C4 (Web Text))

Max Activating Token Index: 990