Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 254 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5535. Min Range: -1.5535

Max Act: 0.9518. Min Act: -0.0000

Data Index: 1115967 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 1.5535. Min Range: -1.5535

Max Act: 1.5535. Min Act: -0.0000

Data Index: 1313749 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 1.5535. Min Range: -1.5535

Max Act: 1.4173. Min Act: -0.0000

Data Index: 627811 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 1.5535. Min Range: -1.5535

Max Act: 1.2628. Min Act: -0.0000

Data Index: 743070 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 1.5535. Min Range: -1.5535

Max Act: 1.1746. Min Act: -0.0000

Data Index: 887943 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 1.5535. Min Range: -1.5535

Max Act: 0.8886. Min Act: -0.0000

Data Index: 835932 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 1.5535. Min Range: -1.5535

Max Act: 0.8347. Min Act: -0.0000

Data Index: 748180 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 1.5535. Min Range: -1.5535

Max Act: 0.6524. Min Act: -0.0000

Data Index: 556530 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 1.5535. Min Range: -1.5535

Max Act: 0.7218. Min Act: -0.0000

Data Index: 255471 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 1.5535. Min Range: -1.5535

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1325683 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 1.5535. Min Range: -1.5535

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1277448 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 1.5535. Min Range: -1.5535

Max Act: 0.8048. Min Act: -0.0000

Data Index: 842585 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 1.5535. Min Range: -1.5535

Max Act: 0.7992. Min Act: -0.0000

Data Index: 838048 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 1.5535. Min Range: -1.5535

Max Act: 0.7095. Min Act: -0.0000

Data Index: 116894 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 1.5535. Min Range: -1.5535

Max Act: 0.7249. Min Act: -0.0000

Data Index: 890033 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 1.5535. Min Range: -1.5535

Max Act: 0.7169. Min Act: -0.0000

Data Index: 943919 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 1.5535. Min Range: -1.5535

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1282010 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 1.5535. Min Range: -1.5535

Max Act: 0.7734. Min Act: -0.0000

Data Index: 274624 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 1.5535. Min Range: -1.5535

Max Act: 0.7864. Min Act: -0.0000

Data Index: 676640 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 1.5535. Min Range: -1.5535

Max Act: 0.7516. Min Act: -0.0000

Data Index: 923964 (C4 (Web Text))

Max Activating Token Index: 374