Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2848 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1701. Min Range: -1.1701

Max Act: 1.1443. Min Act: -0.0000

Data Index: 1295847 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 1.1701. Min Range: -1.1701

Max Act: 1.1337. Min Act: -0.0000

Data Index: 1087803 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 1.1701. Min Range: -1.1701

Max Act: 1.1281. Min Act: -0.0000

Data Index: 724404 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 1.1701. Min Range: -1.1701

Max Act: 1.0629. Min Act: -0.0000

Data Index: 19483 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 1.1701. Min Range: -1.1701

Max Act: 1.0254. Min Act: -0.0000

Data Index: 626014 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 1.1701. Min Range: -1.1701

Max Act: 1.0920. Min Act: -0.0000

Data Index: 442318 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 1.1701. Min Range: -1.1701

Max Act: 1.1701. Min Act: -0.0000

Data Index: 25228 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 1.1701. Min Range: -1.1701

Max Act: 0.9854. Min Act: -0.0000

Data Index: 996094 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 1.1701. Min Range: -1.1701

Max Act: 1.0812. Min Act: -0.0000

Data Index: 1303829 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 1.1701. Min Range: -1.1701

Max Act: 1.0443. Min Act: -0.0000

Data Index: 247146 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 1.1701. Min Range: -1.1701

Max Act: 1.0505. Min Act: -0.0000

Data Index: 12947 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 1.1701. Min Range: -1.1701

Max Act: 1.0501. Min Act: -0.0000

Data Index: 625176 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 1.1701. Min Range: -1.1701

Max Act: 1.0161. Min Act: -0.0000

Data Index: 117304 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 1.1701. Min Range: -1.1701

Max Act: 1.1209. Min Act: -0.0000

Data Index: 1527097 (Python Code)

Max Activating Token Index: 920

Text #14

Max Range: 1.1701. Min Range: -1.1701

Max Act: 0.9445. Min Act: -0.0000

Data Index: 1439735 (Python Code)

Max Activating Token Index: 1007

Text #15

Max Range: 1.1701. Min Range: -1.1701

Max Act: 0.9918. Min Act: -0.0000

Data Index: 816748 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 1.1701. Min Range: -1.1701

Max Act: 0.9061. Min Act: -0.0000

Data Index: 1651795 (Python Code)

Max Activating Token Index: 165

Text #17

Max Range: 1.1701. Min Range: -1.1701

Max Act: 0.9582. Min Act: -0.0000

Data Index: 242571 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 1.1701. Min Range: -1.1701

Max Act: 0.8711. Min Act: -0.0000

Data Index: 647367 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 1.1701. Min Range: -1.1701

Max Act: 0.9535. Min Act: -0.0000

Data Index: 1566987 (Python Code)

Max Activating Token Index: 981