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

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

Neuron 1587 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.4068. Min Act: -0.0000

Data Index: 599004 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3670. Min Act: -0.0000

Data Index: 515779 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.1024. Min Act: -0.0000

Data Index: 603190 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.2358. Min Act: -0.0000

Data Index: 576001 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.1346. Min Act: -0.0000

Data Index: 895317 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.1092. Min Act: -0.0000

Data Index: 489864 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.0876. Min Act: -0.0000

Data Index: 902863 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.0845. Min Act: -0.0000

Data Index: 177605 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.1473. Min Act: -0.0000

Data Index: 301267 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.0974. Min Act: -0.0000

Data Index: 399802 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.0715. Min Act: -0.0000

Data Index: 441671 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.1675. Min Act: -0.0000

Data Index: 94883 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.0843. Min Act: -0.0000

Data Index: 496954 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.0278. Min Act: -0.0000

Data Index: 1050801 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.0620. Min Act: -0.0000

Data Index: 202257 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.1200. Min Act: -0.0000

Data Index: 1210942 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.0544. Min Act: -0.0000

Data Index: 884462 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.0444. Min Act: -0.0000

Data Index: 1312172 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1188135 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 1.4068. Min Range: -1.4068

Max Act: 0.9358. Min Act: -0.0000

Data Index: 422466 (C4 (Web Text))

Max Activating Token Index: 110