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

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

Neuron 2024 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: 0.6936. Min Range: -0.6936

Max Act: 0.6936. Min Act: -0.0000

Data Index: 536019 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6590. Min Act: -0.0000

Data Index: 510849 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1008783 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6443. Min Act: -0.0000

Data Index: 428439 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6363. Min Act: -0.0000

Data Index: 665766 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1006200 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6020. Min Act: -0.0000

Data Index: 132546 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6101. Min Act: -0.0000

Data Index: 735451 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6080. Min Act: -0.0000

Data Index: 15835 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6015. Min Act: -0.0000

Data Index: 263761 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6052. Min Act: -0.0000

Data Index: 428710 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1075351 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5676. Min Act: -0.0000

Data Index: 463955 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6157. Min Act: -0.0000

Data Index: 192024 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1294211 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5540. Min Act: -0.0000

Data Index: 486452 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1054085 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5681. Min Act: -0.0000

Data Index: 146971 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5995. Min Act: -0.0000

Data Index: 721937 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1337964 (C4 (Web Text))

Max Activating Token Index: 709