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

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

Neuron 3712 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.5215. Min Act: -0.0000

Data Index: 16485 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.2726. Min Act: -0.0000

Data Index: 911409 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.2090. Min Act: -0.0000

Data Index: 272546 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.1471. Min Act: -0.0000

Data Index: 391959 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.1002. Min Act: -0.0000

Data Index: 141438 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 1.5215. Min Range: -1.5215

Max Act: 0.9419. Min Act: -0.0000

Data Index: 81729 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.0392. Min Act: -0.0000

Data Index: 1254162 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.0015. Min Act: 0.0000

Data Index: 636766 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 1.5215. Min Range: -1.5215

Max Act: 0.9261. Min Act: -0.0000

Data Index: 408334 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 1.5215. Min Range: -1.5215

Max Act: 0.8516. Min Act: -0.0000

Data Index: 977253 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 1.5215. Min Range: -1.5215

Max Act: 0.7456. Min Act: -0.0000

Data Index: 230198 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 1.5215. Min Range: -1.5215

Max Act: 0.7955. Min Act: -0.0000

Data Index: 424151 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 1.5215. Min Range: -1.5215

Max Act: 0.8041. Min Act: -0.0000

Data Index: 844063 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 1.5215. Min Range: -1.5215

Max Act: 0.7910. Min Act: -0.0000

Data Index: 836590 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 1.5215. Min Range: -1.5215

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1117308 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 1.5215. Min Range: -1.5215

Max Act: 0.8234. Min Act: -0.0000

Data Index: 415749 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 1.5215. Min Range: -1.5215

Max Act: 0.7638. Min Act: -0.0000

Data Index: 399911 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 1.5215. Min Range: -1.5215

Max Act: 0.7484. Min Act: -0.0000

Data Index: 417681 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 1.5215. Min Range: -1.5215

Max Act: 0.7634. Min Act: -0.0000

Data Index: 648448 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 1.5215. Min Range: -1.5215

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1261598 (C4 (Web Text))

Max Activating Token Index: 132