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

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

Neuron 4422 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1254985 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.7028. Min Act: -0.0000

Data Index: 823156 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6911. Min Act: -0.0000

Data Index: 1121350 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1355712 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6671. Min Act: -0.0000

Data Index: 828982 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6033. Min Act: -0.0000

Data Index: 236378 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6833. Min Act: -0.0000

Data Index: 992902 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6255. Min Act: -0.0000

Data Index: 854119 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6184. Min Act: -0.0000

Data Index: 346610 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6158. Min Act: -0.0000

Data Index: 1059717 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1330102 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6033. Min Act: -0.0000

Data Index: 654636 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.5881. Min Act: -0.0000

Data Index: 1034652 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.5827. Min Act: -0.0000

Data Index: 79668 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.5411. Min Act: -0.0000

Data Index: 36059 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1224520 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1155945 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1244076 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1008001 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.5612. Min Act: -0.0000

Data Index: 775881 (C4 (Web Text))

Max Activating Token Index: 217