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

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

Neuron 338 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0090. Min Range: -1.0090

Max Act: 1.0067. Min Act: -0.0000

Data Index: 906114 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 1.0090. Min Range: -1.0090

Max Act: 1.0090. Min Act: -0.0000

Data Index: 104294 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.9379. Min Act: -0.0000

Data Index: 218610 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8998. Min Act: -0.0000

Data Index: 86207 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.9364. Min Act: -0.0000

Data Index: 603051 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8256. Min Act: -0.0000

Data Index: 1138479 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.9062. Min Act: -0.0000

Data Index: 61701 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.9014. Min Act: -0.0000

Data Index: 310612 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8840. Min Act: -0.0000

Data Index: 874734 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8496. Min Act: -0.0000

Data Index: 732872 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8204. Min Act: -0.0000

Data Index: 91853 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8391. Min Act: -0.0000

Data Index: 279752 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8112. Min Act: -0.0000

Data Index: 1027375 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8744. Min Act: -0.0000

Data Index: 273975 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8008. Min Act: -0.0000

Data Index: 707892 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8570. Min Act: -0.0000

Data Index: 829956 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8319. Min Act: -0.0000

Data Index: 510753 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8217. Min Act: -0.0000

Data Index: 812440 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7685. Min Act: -0.0000

Data Index: 1221590 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8137. Min Act: -0.0000

Data Index: 809339 (C4 (Web Text))

Max Activating Token Index: 337