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

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

Neuron 4613 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1559520 (Python Code)

Max Activating Token Index: 591

Text #1

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1528606 (Python Code)

Max Activating Token Index: 260

Text #2

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1561345 (Python Code)

Max Activating Token Index: 424

Text #3

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2821. Min Act: -0.0000

Data Index: 1479463 (Python Code)

Max Activating Token Index: 412

Text #4

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1446567 (Python Code)

Max Activating Token Index: 446

Text #5

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1596213 (Python Code)

Max Activating Token Index: 502

Text #6

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2596. Min Act: -0.0000

Data Index: 1571289 (Python Code)

Max Activating Token Index: 799

Text #7

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1562413 (Python Code)

Max Activating Token Index: 226

Text #8

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2635. Min Act: -0.0000

Data Index: 1440254 (Python Code)

Max Activating Token Index: 735

Text #9

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1468979 (Python Code)

Max Activating Token Index: 822

Text #10

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1585421 (Python Code)

Max Activating Token Index: 795

Text #11

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1520444 (Python Code)

Max Activating Token Index: 776

Text #12

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2451. Min Act: -0.0000

Data Index: 838449 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1566563 (Python Code)

Max Activating Token Index: 428

Text #14

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2445. Min Act: -0.0000

Data Index: 1374095 (Python Code)

Max Activating Token Index: 892

Text #15

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1590024 (Python Code)

Max Activating Token Index: 801

Text #16

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1522713 (Python Code)

Max Activating Token Index: 856

Text #17

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1652500 (Python Code)

Max Activating Token Index: 861

Text #18

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2324. Min Act: -0.0000

Data Index: 1481436 (Python Code)

Max Activating Token Index: 473

Text #19

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1594074 (Python Code)

Max Activating Token Index: 836