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

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

Neuron 3687 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: 0.8002. Min Range: -0.8002

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1254553 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.7731. Min Act: -0.0001

Data Index: 791163 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6051. Min Act: -0.0001

Data Index: 681831 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.7069. Min Act: -0.0001

Data Index: 148514 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.7587. Min Act: -0.0000

Data Index: 749233 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6873. Min Act: -0.0000

Data Index: 1090159 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6367. Min Act: -0.0001

Data Index: 1285128 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6622. Min Act: -0.0000

Data Index: 454087 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6521. Min Act: -0.0001

Data Index: 776799 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.5585. Min Act: -0.0001

Data Index: 935418 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.5810. Min Act: -0.0000

Data Index: 571092 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6017. Min Act: -0.0001

Data Index: 910699 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.5373. Min Act: -0.0001

Data Index: 897644 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.5481. Min Act: -0.0001

Data Index: 565241 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.5409. Min Act: -0.0001

Data Index: 746956 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.5827. Min Act: -0.0001

Data Index: 1153895 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6327. Min Act: -0.0001

Data Index: 507675 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.5325. Min Act: -0.0000

Data Index: 618768 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.5436. Min Act: -0.0001

Data Index: 651776 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.5290. Min Act: -0.0001

Data Index: 434762 (C4 (Web Text))

Max Activating Token Index: 914