Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 799 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1129. Min Range: -1.1129

Max Act: 1.1129. Min Act: -0.0000

Data Index: 1347729 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.8130. Min Act: -0.0001

Data Index: 1093484 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.8191. Min Act: -0.0000

Data Index: 88006 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.7285. Min Act: -0.0000

Data Index: 780260 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.7230. Min Act: -0.0001

Data Index: 1394409 (Python Code)

Max Activating Token Index: 704

Text #5

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.7588. Min Act: -0.0000

Data Index: 273754 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.7384. Min Act: -0.0001

Data Index: 1597374 (Python Code)

Max Activating Token Index: 391

Text #7

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.7398. Min Act: -0.0001

Data Index: 1250646 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.6736. Min Act: -0.0001

Data Index: 1563420 (Python Code)

Max Activating Token Index: 704

Text #9

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.6463. Min Act: -0.0000

Data Index: 1205723 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.6667. Min Act: -0.0001

Data Index: 1651970 (Python Code)

Max Activating Token Index: 208

Text #11

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.5941. Min Act: -0.0000

Data Index: 16881 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.6274. Min Act: -0.0000

Data Index: 824762 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1252868 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.6278. Min Act: -0.0000

Data Index: 432026 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.6168. Min Act: -0.0001

Data Index: 149222 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.6387. Min Act: -0.0000

Data Index: 864753 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.5995. Min Act: -0.0000

Data Index: 726161 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.5743. Min Act: -0.0000

Data Index: 29880 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.5859. Min Act: -0.0000

Data Index: 716711 (C4 (Web Text))

Max Activating Token Index: 604