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

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

Neuron 1410 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: 0.7355. Min Range: -0.7355

Max Act: 0.7355. Min Act: -0.0000

Data Index: 1574316 (Python Code)

Max Activating Token Index: 265

Text #1

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6930. Min Act: -0.0000

Data Index: 1509139 (Python Code)

Max Activating Token Index: 672

Text #2

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1513381 (Python Code)

Max Activating Token Index: 604

Text #3

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1655269 (Python Code)

Max Activating Token Index: 874

Text #4

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6964. Min Act: -0.0001

Data Index: 1578962 (Python Code)

Max Activating Token Index: 448

Text #5

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.5879. Min Act: -0.0001

Data Index: 1581255 (Python Code)

Max Activating Token Index: 938

Text #6

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6256. Min Act: -0.0000

Data Index: 1560466 (Python Code)

Max Activating Token Index: 295

Text #7

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1609548 (Python Code)

Max Activating Token Index: 223

Text #8

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1571227 (Python Code)

Max Activating Token Index: 193

Text #9

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1405942 (Python Code)

Max Activating Token Index: 665

Text #10

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1529091 (Python Code)

Max Activating Token Index: 148

Text #11

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.5862. Min Act: -0.0001

Data Index: 1595891 (Python Code)

Max Activating Token Index: 281

Text #12

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6398. Min Act: -0.0000

Data Index: 703745 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6172. Min Act: -0.0001

Data Index: 1510763 (Python Code)

Max Activating Token Index: 651

Text #14

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1583495 (Python Code)

Max Activating Token Index: 97

Text #15

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6300. Min Act: -0.0000

Data Index: 1538096 (Python Code)

Max Activating Token Index: 741

Text #16

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1519431 (Python Code)

Max Activating Token Index: 799

Text #17

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1420001 (Python Code)

Max Activating Token Index: 787

Text #18

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6357. Min Act: -0.0000

Data Index: 1414589 (Python Code)

Max Activating Token Index: 285

Text #19

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1508306 (Python Code)

Max Activating Token Index: 860