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

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

Neuron 4009 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: 0.0950. Min Range: -0.0950

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1337102 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0814. Min Act: -0.0001

Data Index: 479316 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0781. Min Act: -0.0000

Data Index: 641414 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0788. Min Act: -0.0001

Data Index: 613445 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0795. Min Act: -0.0000

Data Index: 766045 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1183322 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0722. Min Act: -0.0000

Data Index: 1161474 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1307063 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0740. Min Act: -0.0000

Data Index: 684453 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0733. Min Act: -0.0000

Data Index: 1258093 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0694. Min Act: -0.0000

Data Index: 233028 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0745. Min Act: -0.0000

Data Index: 564554 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0748. Min Act: -0.0001

Data Index: 1603828 (Python Code)

Max Activating Token Index: 862

Text #13

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0733. Min Act: -0.0000

Data Index: 939537 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0683. Min Act: -0.0000

Data Index: 1343957 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0678. Min Act: -0.0000

Data Index: 505009 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0662. Min Act: -0.0000

Data Index: 391766 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0677. Min Act: -0.0000

Data Index: 149924 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0686. Min Act: -0.0000

Data Index: 902839 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1120150 (C4 (Web Text))

Max Activating Token Index: 988