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

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

Neuron 3187 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4830. Min Act: -0.0000

Data Index: 959957 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4789. Min Act: -0.0000

Data Index: 398809 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4022. Min Act: -0.0000

Data Index: 237401 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3511. Min Act: -0.0000

Data Index: 1334556 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3804. Min Act: -0.0000

Data Index: 1584438 (Python Code)

Max Activating Token Index: 214

Text #5

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3496. Min Act: -0.0000

Data Index: 1506710 (Python Code)

Max Activating Token Index: 532

Text #6

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3352. Min Act: -0.0000

Data Index: 1633303 (Python Code)

Max Activating Token Index: 795

Text #7

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1520579 (Python Code)

Max Activating Token Index: 136

Text #8

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1521163 (Python Code)

Max Activating Token Index: 351

Text #9

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.2957. Min Act: -0.0000

Data Index: 764038 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3498. Min Act: -0.0000

Data Index: 1562054 (Python Code)

Max Activating Token Index: 976

Text #11

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1274413 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3332. Min Act: -0.0000

Data Index: 1531822 (Python Code)

Max Activating Token Index: 909

Text #13

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1485690 (Python Code)

Max Activating Token Index: 813

Text #14

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1046141 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1486621 (Python Code)

Max Activating Token Index: 881

Text #16

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3226. Min Act: -0.0000

Data Index: 154939 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3176. Min Act: -0.0000

Data Index: 86132 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3250. Min Act: -0.0000

Data Index: 1096828 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.4830. Min Range: -0.4830

Max Act: 0.3056. Min Act: -0.0000

Data Index: 167648 (C4 (Web Text))

Max Activating Token Index: 1008