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

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

Neuron 2012 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.6250. Min Act: -0.0000

Data Index: 1012010 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.5049. Min Act: -0.0000

Data Index: 1281918 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.2782. Min Act: -0.0000

Data Index: 440435 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.2671. Min Act: -0.0000

Data Index: 235786 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.2551. Min Act: -0.0000

Data Index: 924525 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.2577. Min Act: -0.0000

Data Index: 122125 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.2995. Min Act: -0.0000

Data Index: 800671 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.1733. Min Act: -0.0000

Data Index: 464438 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.2453. Min Act: -0.0000

Data Index: 632235 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.2280. Min Act: -0.0000

Data Index: 1186846 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.1874. Min Act: -0.0000

Data Index: 1382979 (Python Code)

Max Activating Token Index: 166

Text #11

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.1774. Min Act: -0.0000

Data Index: 452556 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.1650. Min Act: -0.0000

Data Index: 918536 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.1946. Min Act: -0.0000

Data Index: 91516 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.1550. Min Act: -0.0000

Data Index: 468898 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.1818. Min Act: -0.0000

Data Index: 85930 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.1870. Min Act: -0.0000

Data Index: 281979 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.1452. Min Act: -0.0000

Data Index: 403385 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.1713. Min Act: -0.0000

Data Index: 1122467 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.1662. Min Act: -0.0000

Data Index: 776519 (C4 (Web Text))

Max Activating Token Index: 213