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

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

Neuron 5529 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.7613. Min Act: -0.0000

Data Index: 904874 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.6366. Min Act: -0.0000

Data Index: 1060380 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.5054. Min Act: -0.0000

Data Index: 1289771 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.4157. Min Act: -0.0000

Data Index: 1100670 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.4338. Min Act: -0.0000

Data Index: 436035 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.3390. Min Act: -0.0000

Data Index: 554118 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.2432. Min Act: -0.0000

Data Index: 587149 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.2257. Min Act: -0.0000

Data Index: 596903 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.2551. Min Act: -0.0000

Data Index: 800478 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.1583. Min Act: -0.0000

Data Index: 1520655 (Python Code)

Max Activating Token Index: 874

Text #10

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.1960. Min Act: -0.0000

Data Index: 210114 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.1881. Min Act: -0.0000

Data Index: 188546 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.2431. Min Act: -0.0000

Data Index: 436600 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.1105. Min Act: -0.0000

Data Index: 446975 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.1287. Min Act: -0.0000

Data Index: 1051312 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.1231. Min Act: -0.0000

Data Index: 1200003 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.1242. Min Act: -0.0000

Data Index: 743621 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.0395. Min Act: -0.0000

Data Index: 889391 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.0317. Min Act: -0.0000

Data Index: 97352 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 1.7613. Min Range: -1.7613

Max Act: 1.0946. Min Act: -0.0000

Data Index: 5284 (C4 (Web Text))

Max Activating Token Index: 534