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

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

Neuron 1942 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: 3.2528. Min Range: -3.2528

Max Act: 3.2528. Min Act: -0.0000

Data Index: 1608381 (Python Code)

Max Activating Token Index: 707

Text #1

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.6937. Min Act: -0.0000

Data Index: 414865 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.6311. Min Act: -0.0000

Data Index: 294265 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.6858. Min Act: -0.0000

Data Index: 558798 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.3538. Min Act: -0.0000

Data Index: 325372 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.3219. Min Act: -0.0000

Data Index: 1369018 (Python Code)

Max Activating Token Index: 447

Text #6

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.5280. Min Act: -0.0000

Data Index: 1374105 (Python Code)

Max Activating Token Index: 340

Text #7

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.3898. Min Act: -0.0000

Data Index: 1645898 (Python Code)

Max Activating Token Index: 821

Text #8

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.2534. Min Act: -0.0000

Data Index: 1564288 (Python Code)

Max Activating Token Index: 317

Text #9

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.4769. Min Act: -0.0000

Data Index: 1378406 (Python Code)

Max Activating Token Index: 165

Text #10

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.2158. Min Act: -0.0000

Data Index: 1368351 (Python Code)

Max Activating Token Index: 289

Text #11

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.2886. Min Act: -0.0000

Data Index: 65368 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.2007. Min Act: -0.0000

Data Index: 1440598 (Python Code)

Max Activating Token Index: 452

Text #13

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.1438. Min Act: -0.0000

Data Index: 283814 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.1228. Min Act: 0.0000

Data Index: 1391239 (Python Code)

Max Activating Token Index: 326

Text #15

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.2431. Min Act: -0.0000

Data Index: 1389013 (Python Code)

Max Activating Token Index: 403

Text #16

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.2769. Min Act: -0.0000

Data Index: 1522459 (Python Code)

Max Activating Token Index: 236

Text #17

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.1990. Min Act: -0.0000

Data Index: 1004461 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.3121. Min Act: -0.0000

Data Index: 205842 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 3.2528. Min Range: -3.2528

Max Act: 2.1034. Min Act: -0.0000

Data Index: 1391085 (Python Code)

Max Activating Token Index: 162