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

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

Neuron 2193 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: 1.6680. Min Range: -1.6680

Max Act: 1.6680. Min Act: -0.0000

Data Index: 1225230 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 1.6680. Min Range: -1.6680

Max Act: 1.5346. Min Act: -0.0000

Data Index: 683569 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 1.6680. Min Range: -1.6680

Max Act: 1.0936. Min Act: -0.0000

Data Index: 411158 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 1.6680. Min Range: -1.6680

Max Act: 1.1167. Min Act: -0.0000

Data Index: 274482 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 1.6680. Min Range: -1.6680

Max Act: 1.0818. Min Act: -0.0000

Data Index: 1247197 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 1.6680. Min Range: -1.6680

Max Act: 0.9001. Min Act: -0.0000

Data Index: 1054295 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 1.6680. Min Range: -1.6680

Max Act: 0.9964. Min Act: -0.0000

Data Index: 413102 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 1.6680. Min Range: -1.6680

Max Act: 0.9572. Min Act: -0.0000

Data Index: 883033 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 1.6680. Min Range: -1.6680

Max Act: 1.0029. Min Act: -0.0000

Data Index: 22428 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 1.6680. Min Range: -1.6680

Max Act: 0.9652. Min Act: -0.0000

Data Index: 288329 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 1.6680. Min Range: -1.6680

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1109871 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 1.6680. Min Range: -1.6680

Max Act: 0.9165. Min Act: -0.0000

Data Index: 1043874 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 1.6680. Min Range: -1.6680

Max Act: 0.9116. Min Act: -0.0000

Data Index: 135753 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 1.6680. Min Range: -1.6680

Max Act: 0.9040. Min Act: -0.0000

Data Index: 10162 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 1.6680. Min Range: -1.6680

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1144779 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 1.6680. Min Range: -1.6680

Max Act: 0.8702. Min Act: -0.0000

Data Index: 892033 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 1.6680. Min Range: -1.6680

Max Act: 0.8995. Min Act: -0.0000

Data Index: 376060 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 1.6680. Min Range: -1.6680

Max Act: 0.8594. Min Act: -0.0000

Data Index: 921548 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 1.6680. Min Range: -1.6680

Max Act: 0.8537. Min Act: -0.0000

Data Index: 14351 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 1.6680. Min Range: -1.6680

Max Act: 0.9095. Min Act: -0.0000

Data Index: 1155383 (C4 (Web Text))

Max Activating Token Index: 295