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

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

Neuron 403 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6355. Min Range: -3.6355

Max Act: 3.6355. Min Act: -0.0000

Data Index: 1547929 (Python Code)

Max Activating Token Index: 516

Text #1

Max Range: 3.6355. Min Range: -3.6355

Max Act: 3.2775. Min Act: -0.0000

Data Index: 1529848 (Python Code)

Max Activating Token Index: 555

Text #2

Max Range: 3.6355. Min Range: -3.6355

Max Act: 3.1404. Min Act: -0.0000

Data Index: 1427880 (Python Code)

Max Activating Token Index: 419

Text #3

Max Range: 3.6355. Min Range: -3.6355

Max Act: 2.9594. Min Act: -0.0000

Data Index: 1375427 (Python Code)

Max Activating Token Index: 291

Text #4

Max Range: 3.6355. Min Range: -3.6355

Max Act: 3.0471. Min Act: -0.0000

Data Index: 1389293 (Python Code)

Max Activating Token Index: 247

Text #5

Max Range: 3.6355. Min Range: -3.6355

Max Act: 3.1408. Min Act: -0.0000

Data Index: 1410578 (Python Code)

Max Activating Token Index: 369

Text #6

Max Range: 3.6355. Min Range: -3.6355

Max Act: 2.8808. Min Act: -0.0000

Data Index: 1576989 (Python Code)

Max Activating Token Index: 522

Text #7

Max Range: 3.6355. Min Range: -3.6355

Max Act: 2.6092. Min Act: -0.0000

Data Index: 1463713 (Python Code)

Max Activating Token Index: 249

Text #8

Max Range: 3.6355. Min Range: -3.6355

Max Act: 2.3872. Min Act: -0.0000

Data Index: 1560743 (Python Code)

Max Activating Token Index: 160

Text #9

Max Range: 3.6355. Min Range: -3.6355

Max Act: 2.5715. Min Act: -0.0000

Data Index: 1556003 (Python Code)

Max Activating Token Index: 40

Text #10

Max Range: 3.6355. Min Range: -3.6355

Max Act: 2.6580. Min Act: -0.0000

Data Index: 1544971 (Python Code)

Max Activating Token Index: 458

Text #11

Max Range: 3.6355. Min Range: -3.6355

Max Act: 2.3579. Min Act: -0.0000

Data Index: 1588035 (Python Code)

Max Activating Token Index: 537

Text #12

Max Range: 3.6355. Min Range: -3.6355

Max Act: 2.4744. Min Act: -0.0000

Data Index: 1471918 (Python Code)

Max Activating Token Index: 709

Text #13

Max Range: 3.6355. Min Range: -3.6355

Max Act: 2.4449. Min Act: -0.0000

Data Index: 1634259 (Python Code)

Max Activating Token Index: 139

Text #14

Max Range: 3.6355. Min Range: -3.6355

Max Act: 2.4552. Min Act: -0.0000

Data Index: 1645623 (Python Code)

Max Activating Token Index: 577

Text #15

Max Range: 3.6355. Min Range: -3.6355

Max Act: 2.3853. Min Act: -0.0000

Data Index: 1517499 (Python Code)

Max Activating Token Index: 626

Text #16

Max Range: 3.6355. Min Range: -3.6355

Max Act: 2.3751. Min Act: -0.0000

Data Index: 1584050 (Python Code)

Max Activating Token Index: 541

Text #17

Max Range: 3.6355. Min Range: -3.6355

Max Act: 2.1869. Min Act: -0.0000

Data Index: 1584166 (Python Code)

Max Activating Token Index: 971

Text #18

Max Range: 3.6355. Min Range: -3.6355

Max Act: 2.3182. Min Act: -0.0000

Data Index: 1547216 (Python Code)

Max Activating Token Index: 1011

Text #19

Max Range: 3.6355. Min Range: -3.6355

Max Act: 2.0006. Min Act: -0.0000

Data Index: 1434896 (Python Code)

Max Activating Token Index: 836