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

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

Neuron 605 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6840. Min Range: -2.6840

Max Act: 2.3371. Min Act: -0.0000

Data Index: 1102321 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 2.6840. Min Range: -2.6840

Max Act: 2.4747. Min Act: -0.0000

Data Index: 1173253 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 2.6840. Min Range: -2.6840

Max Act: 2.6840. Min Act: -0.0000

Data Index: 1129539 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 2.6840. Min Range: -2.6840

Max Act: 2.4367. Min Act: -0.0000

Data Index: 1263362 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 2.6840. Min Range: -2.6840

Max Act: 2.5233. Min Act: -0.0000

Data Index: 490810 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 2.6840. Min Range: -2.6840

Max Act: 2.2642. Min Act: -0.0000

Data Index: 88910 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 2.6840. Min Range: -2.6840

Max Act: 2.0152. Min Act: -0.0000

Data Index: 643746 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 2.6840. Min Range: -2.6840

Max Act: 2.1802. Min Act: -0.0000

Data Index: 1012945 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 2.6840. Min Range: -2.6840

Max Act: 2.1585. Min Act: -0.0000

Data Index: 915083 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 2.6840. Min Range: -2.6840

Max Act: 2.0314. Min Act: -0.0000

Data Index: 111678 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 2.6840. Min Range: -2.6840

Max Act: 1.9560. Min Act: -0.0001

Data Index: 166818 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 2.6840. Min Range: -2.6840

Max Act: 2.0916. Min Act: -0.0000

Data Index: 952645 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 2.6840. Min Range: -2.6840

Max Act: 2.1912. Min Act: -0.0000

Data Index: 608307 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 2.6840. Min Range: -2.6840

Max Act: 2.0892. Min Act: -0.0000

Data Index: 210334 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 2.6840. Min Range: -2.6840

Max Act: 2.0645. Min Act: -0.0000

Data Index: 987258 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 2.6840. Min Range: -2.6840

Max Act: 2.0459. Min Act: -0.0000

Data Index: 1264916 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 2.6840. Min Range: -2.6840

Max Act: 1.9271. Min Act: -0.0000

Data Index: 1237091 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 2.6840. Min Range: -2.6840

Max Act: 2.0316. Min Act: -0.0000

Data Index: 530563 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 2.6840. Min Range: -2.6840

Max Act: 2.0281. Min Act: -0.0000

Data Index: 1253984 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 2.6840. Min Range: -2.6840

Max Act: 2.0011. Min Act: -0.0000

Data Index: 645014 (C4 (Web Text))

Max Activating Token Index: 406