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

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

Neuron 51 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: 1.3380. Min Range: -1.3380

Max Act: 1.3380. Min Act: -0.0000

Data Index: 606558 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.0494. Min Act: -0.0000

Data Index: 580473 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.9018. Min Act: -0.0000

Data Index: 155146 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.9069. Min Act: -0.0000

Data Index: 595675 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8855. Min Act: -0.0000

Data Index: 913779 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1129463 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8429. Min Act: -0.0000

Data Index: 1048066 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1022544 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8280. Min Act: -0.0000

Data Index: 105816 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8181. Min Act: -0.0000

Data Index: 838184 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7858. Min Act: -0.0000

Data Index: 93076 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1446687 (Python Code)

Max Activating Token Index: 451

Text #12

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7977. Min Act: -0.0000

Data Index: 980591 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7772. Min Act: -0.0000

Data Index: 814930 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1291171 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7227. Min Act: -0.0000

Data Index: 687273 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7672. Min Act: -0.0000

Data Index: 758645 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7584. Min Act: -0.0000

Data Index: 527664 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7521. Min Act: -0.0000

Data Index: 840323 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7535. Min Act: -0.0000

Data Index: 32664 (C4 (Web Text))

Max Activating Token Index: 299