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

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

Neuron 2896 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.6650. Min Act: -0.0000

Data Index: 860001 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5947. Min Act: -0.0000

Data Index: 535052 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5635. Min Act: -0.0000

Data Index: 276998 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1357417 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5070. Min Act: -0.0000

Data Index: 161302 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1094527 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5516. Min Act: -0.0000

Data Index: 71353 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5236. Min Act: -0.0000

Data Index: 151916 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1013595 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4952. Min Act: -0.0000

Data Index: 666700 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4744. Min Act: -0.0000

Data Index: 1063799 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4540. Min Act: -0.0000

Data Index: 501706 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4658. Min Act: -0.0000

Data Index: 61722 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4655. Min Act: -0.0000

Data Index: 1197822 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4551. Min Act: -0.0000

Data Index: 1334358 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4725. Min Act: -0.0000

Data Index: 150890 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4615. Min Act: -0.0000

Data Index: 513358 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4265. Min Act: -0.0000

Data Index: 518031 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1076712 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1313037 (C4 (Web Text))

Max Activating Token Index: 906