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

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

Neuron 33 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: 0.1026. Min Range: -0.1026

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1083715 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0915. Min Act: -0.0000

Data Index: 77876 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0837. Min Act: -0.0001

Data Index: 1597062 (Python Code)

Max Activating Token Index: 642

Text #3

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0861. Min Act: -0.0001

Data Index: 1373923 (Python Code)

Max Activating Token Index: 938

Text #4

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0888. Min Act: -0.0001

Data Index: 546722 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0886. Min Act: -0.0000

Data Index: 369125 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0894. Min Act: -0.0000

Data Index: 59711 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1303517 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0868. Min Act: -0.0000

Data Index: 408423 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0806. Min Act: -0.0001

Data Index: 384565 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0759. Min Act: -0.0001

Data Index: 557115 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1174605 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0768. Min Act: -0.0000

Data Index: 508822 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0728. Min Act: -0.0001

Data Index: 81291 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0747. Min Act: -0.0001

Data Index: 1047071 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0750. Min Act: -0.0001

Data Index: 311141 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0696. Min Act: -0.0001

Data Index: 83485 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0691. Min Act: -0.0001

Data Index: 356236 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0726. Min Act: -0.0000

Data Index: 1295720 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0724. Min Act: -0.0000

Data Index: 113207 (C4 (Web Text))

Max Activating Token Index: 1015