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

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

Neuron 3400 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0429. Min Range: -1.0429

Max Act: 1.0429. Min Act: -0.0000

Data Index: 1033330 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8483. Min Act: -0.0000

Data Index: 190992 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8350. Min Act: -0.0000

Data Index: 23897 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8521. Min Act: -0.0000

Data Index: 818823 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.9437. Min Act: -0.0000

Data Index: 1197442 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.7614. Min Act: -0.0000

Data Index: 1155402 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1202207 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1168566 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.6556. Min Act: -0.0000

Data Index: 702976 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1034363 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1230335 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.5210. Min Act: -0.0000

Data Index: 1535090 (Python Code)

Max Activating Token Index: 543

Text #12

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1500930 (Python Code)

Max Activating Token Index: 700

Text #13

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1615003 (Python Code)

Max Activating Token Index: 238

Text #14

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.5021. Min Act: -0.0000

Data Index: 897885 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1582268 (Python Code)

Max Activating Token Index: 329

Text #16

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.4772. Min Act: -0.0000

Data Index: 1636862 (Python Code)

Max Activating Token Index: 443

Text #17

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.4537. Min Act: -0.0000

Data Index: 236284 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1630449 (Python Code)

Max Activating Token Index: 98

Text #19

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.4516. Min Act: 0.0000

Data Index: 1506451 (Python Code)

Max Activating Token Index: 78