Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 184 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.8380. Min Act: -0.0000

Data Index: 1394763 (Python Code)

Max Activating Token Index: 966

Text #1

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7379. Min Act: -0.0000

Data Index: 1458891 (Python Code)

Max Activating Token Index: 719

Text #2

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1642430 (Python Code)

Max Activating Token Index: 453

Text #3

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1632252 (Python Code)

Max Activating Token Index: 764

Text #4

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1477073 (Python Code)

Max Activating Token Index: 661

Text #5

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1430496 (Python Code)

Max Activating Token Index: 468

Text #6

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7409. Min Act: -0.0000

Data Index: 1613520 (Python Code)

Max Activating Token Index: 619

Text #7

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6917. Min Act: -0.0000

Data Index: 1439213 (Python Code)

Max Activating Token Index: 190

Text #8

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6511. Min Act: -0.0000

Data Index: 1631464 (Python Code)

Max Activating Token Index: 327

Text #9

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1625921 (Python Code)

Max Activating Token Index: 611

Text #10

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6506. Min Act: -0.0000

Data Index: 1382904 (Python Code)

Max Activating Token Index: 601

Text #11

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6325. Min Act: -0.0000

Data Index: 1430083 (Python Code)

Max Activating Token Index: 646

Text #12

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5660. Min Act: -0.0000

Data Index: 1483185 (Python Code)

Max Activating Token Index: 334

Text #13

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5744. Min Act: -0.0000

Data Index: 505369 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1393102 (Python Code)

Max Activating Token Index: 363

Text #15

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1603772 (Python Code)

Max Activating Token Index: 196

Text #16

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5343. Min Act: -0.0000

Data Index: 1434688 (Python Code)

Max Activating Token Index: 182

Text #17

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1488385 (Python Code)

Max Activating Token Index: 919

Text #18

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1360449 (Python Code)

Max Activating Token Index: 1020

Text #19

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5077. Min Act: -0.0000

Data Index: 922616 (C4 (Web Text))

Max Activating Token Index: 444