Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 813 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.7343. Min Act: -0.0001

Data Index: 1058906 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.7289. Min Act: -0.0001

Data Index: 108370 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.4314. Min Act: -0.0001

Data Index: 664560 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.2637. Min Act: -0.0001

Data Index: 153519 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.2570. Min Act: -0.0001

Data Index: 704120 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.2872. Min Act: -0.0001

Data Index: 768702 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.0535. Min Act: -0.0001

Data Index: 431378 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.1502. Min Act: -0.0001

Data Index: 704171 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.2114. Min Act: -0.0001

Data Index: 209328 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.2731. Min Act: -0.0001

Data Index: 1184 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.2700. Min Act: -0.0001

Data Index: 686416 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.1782. Min Act: -0.0001

Data Index: 238240 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.1746. Min Act: -0.0001

Data Index: 450551 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.1579. Min Act: -0.0001

Data Index: 90901 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.1196. Min Act: -0.0001

Data Index: 18110 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.0716. Min Act: -0.0000

Data Index: 450573 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.2802. Min Act: -0.0001

Data Index: 698483 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.1008. Min Act: -0.0001

Data Index: 979936 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.1408. Min Act: -0.0000

Data Index: 706234 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.0486. Min Act: -0.0001

Data Index: 216583 (C4 (Web Text))

Max Activating Token Index: 594