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

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

Neuron 3647 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.7060. Min Act: -0.0002

Data Index: 1301599 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.7879. Min Act: -0.0002

Data Index: 802746 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.5731. Min Act: -0.0002

Data Index: 1267488 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.7202. Min Act: -0.0002

Data Index: 462237 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.5775. Min Act: -0.0002

Data Index: 220183 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.5632. Min Act: -0.0002

Data Index: 1153618 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.4892. Min Act: -0.0002

Data Index: 350578 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.5995. Min Act: -0.0002

Data Index: 227216 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.3959. Min Act: -0.0002

Data Index: 1194642 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.6551. Min Act: -0.0002

Data Index: 405085 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.4245. Min Act: -0.0002

Data Index: 333329 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.5193. Min Act: -0.0002

Data Index: 1315921 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.3688. Min Act: -0.0002

Data Index: 1070130 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.4654. Min Act: -0.0002

Data Index: 1305390 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.5203. Min Act: -0.0002

Data Index: 19673 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.3519. Min Act: -0.0002

Data Index: 964196 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.4085. Min Act: -0.0002

Data Index: 429230 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.1631. Min Act: -0.0002

Data Index: 1171648 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.4409. Min Act: -0.0002

Data Index: 713585 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.4539. Min Act: -0.0002

Data Index: 926088 (C4 (Web Text))

Max Activating Token Index: 85