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

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

Neuron 288 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3238. Min Act: -0.0002

Data Index: 1436403 (Python Code)

Max Activating Token Index: 391

Text #1

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2995. Min Act: -0.0002

Data Index: 1466495 (Python Code)

Max Activating Token Index: 428

Text #2

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2729. Min Act: -0.0002

Data Index: 1651954 (Python Code)

Max Activating Token Index: 1013

Text #3

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2696. Min Act: -0.0002

Data Index: 1450788 (Python Code)

Max Activating Token Index: 26

Text #4

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2791. Min Act: -0.0002

Data Index: 1176353 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2615. Min Act: -0.0002

Data Index: 1501831 (Python Code)

Max Activating Token Index: 55

Text #6

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2681. Min Act: -0.0002

Data Index: 1463464 (Python Code)

Max Activating Token Index: 488

Text #7

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2721. Min Act: -0.0002

Data Index: 1490311 (Python Code)

Max Activating Token Index: 203

Text #8

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2746. Min Act: -0.0002

Data Index: 1533689 (Python Code)

Max Activating Token Index: 91

Text #9

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2623. Min Act: -0.0002

Data Index: 1471687 (Python Code)

Max Activating Token Index: 258

Text #10

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2619. Min Act: -0.0002

Data Index: 1373551 (Python Code)

Max Activating Token Index: 569

Text #11

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2728. Min Act: -0.0002

Data Index: 1524236 (Python Code)

Max Activating Token Index: 137

Text #12

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2820. Min Act: -0.0002

Data Index: 1494644 (Python Code)

Max Activating Token Index: 428

Text #13

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2436. Min Act: -0.0002

Data Index: 1495167 (Python Code)

Max Activating Token Index: 1011

Text #14

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2709. Min Act: -0.0002

Data Index: 1531970 (Python Code)

Max Activating Token Index: 241

Text #15

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2642. Min Act: -0.0002

Data Index: 1508723 (Python Code)

Max Activating Token Index: 123

Text #16

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2593. Min Act: -0.0002

Data Index: 1434881 (Python Code)

Max Activating Token Index: 26

Text #17

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2663. Min Act: -0.0002

Data Index: 1397189 (Python Code)

Max Activating Token Index: 384

Text #18

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2776. Min Act: -0.0002

Data Index: 1398535 (Python Code)

Max Activating Token Index: 63

Text #19

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2481. Min Act: -0.0002

Data Index: 1655277 (Python Code)

Max Activating Token Index: 171