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

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

Neuron 507 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9829. Min Range: -2.9829

Max Act: 2.9829. Min Act: -0.0000

Data Index: 1399821 (Python Code)

Max Activating Token Index: 289

Text #1

Max Range: 2.9829. Min Range: -2.9829

Max Act: 2.8168. Min Act: -0.0000

Data Index: 1543051 (Python Code)

Max Activating Token Index: 811

Text #2

Max Range: 2.9829. Min Range: -2.9829

Max Act: 2.5408. Min Act: -0.0000

Data Index: 1631987 (Python Code)

Max Activating Token Index: 863

Text #3

Max Range: 2.9829. Min Range: -2.9829

Max Act: 2.5330. Min Act: 0.0000

Data Index: 1545549 (Python Code)

Max Activating Token Index: 66

Text #4

Max Range: 2.9829. Min Range: -2.9829

Max Act: 2.7959. Min Act: 0.0000

Data Index: 1058793 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 2.9829. Min Range: -2.9829

Max Act: 2.4509. Min Act: -0.0000

Data Index: 1426459 (Python Code)

Max Activating Token Index: 680

Text #6

Max Range: 2.9829. Min Range: -2.9829

Max Act: 2.4199. Min Act: -0.0000

Data Index: 1388946 (Python Code)

Max Activating Token Index: 958

Text #7

Max Range: 2.9829. Min Range: -2.9829

Max Act: 2.1821. Min Act: 0.0000

Data Index: 1458105 (Python Code)

Max Activating Token Index: 100

Text #8

Max Range: 2.9829. Min Range: -2.9829

Max Act: 1.9599. Min Act: -0.0000

Data Index: 1577866 (Python Code)

Max Activating Token Index: 803

Text #9

Max Range: 2.9829. Min Range: -2.9829

Max Act: 2.0201. Min Act: -0.0000

Data Index: 1626957 (Python Code)

Max Activating Token Index: 736

Text #10

Max Range: 2.9829. Min Range: -2.9829

Max Act: 1.9016. Min Act: -0.0000

Data Index: 1572102 (Python Code)

Max Activating Token Index: 217

Text #11

Max Range: 2.9829. Min Range: -2.9829

Max Act: 1.9536. Min Act: 0.0000

Data Index: 1544269 (Python Code)

Max Activating Token Index: 594

Text #12

Max Range: 2.9829. Min Range: -2.9829

Max Act: 1.7841. Min Act: -0.0000

Data Index: 1507389 (Python Code)

Max Activating Token Index: 954

Text #13

Max Range: 2.9829. Min Range: -2.9829

Max Act: 1.7930. Min Act: -0.0000

Data Index: 193789 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 2.9829. Min Range: -2.9829

Max Act: 1.7588. Min Act: -0.0000

Data Index: 1411170 (Python Code)

Max Activating Token Index: 28

Text #15

Max Range: 2.9829. Min Range: -2.9829

Max Act: 1.8328. Min Act: -0.0000

Data Index: 513149 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 2.9829. Min Range: -2.9829

Max Act: 1.6385. Min Act: 0.0000

Data Index: 1382322 (Python Code)

Max Activating Token Index: 38

Text #17

Max Range: 2.9829. Min Range: -2.9829

Max Act: 1.7876. Min Act: -0.0000

Data Index: 1454392 (Python Code)

Max Activating Token Index: 173

Text #18

Max Range: 2.9829. Min Range: -2.9829

Max Act: 1.6763. Min Act: 0.0000

Data Index: 1545032 (Python Code)

Max Activating Token Index: 505

Text #19

Max Range: 2.9829. Min Range: -2.9829

Max Act: 1.7572. Min Act: -0.0000

Data Index: 1028280 (C4 (Web Text))

Max Activating Token Index: 838