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

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

Neuron 5018 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.9687. Min Act: -0.0000

Data Index: 1534266 (Python Code)

Max Activating Token Index: 161

Text #1

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.7227. Min Act: -0.0000

Data Index: 1399372 (Python Code)

Max Activating Token Index: 405

Text #2

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.5871. Min Act: -0.0000

Data Index: 1510922 (Python Code)

Max Activating Token Index: 908

Text #3

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.8179. Min Act: -0.0000

Data Index: 1539878 (Python Code)

Max Activating Token Index: 931

Text #4

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.6204. Min Act: -0.0000

Data Index: 1511805 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.5254. Min Act: -0.0000

Data Index: 1408692 (Python Code)

Max Activating Token Index: 628

Text #6

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.4989. Min Act: -0.0000

Data Index: 1593141 (Python Code)

Max Activating Token Index: 41

Text #7

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.5388. Min Act: -0.0000

Data Index: 1623243 (Python Code)

Max Activating Token Index: 151

Text #8

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.3976. Min Act: -0.0000

Data Index: 1630821 (Python Code)

Max Activating Token Index: 546

Text #9

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.4442. Min Act: -0.0000

Data Index: 1393056 (Python Code)

Max Activating Token Index: 104

Text #10

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.4806. Min Act: -0.0000

Data Index: 1533869 (Python Code)

Max Activating Token Index: 730

Text #11

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.4396. Min Act: -0.0000

Data Index: 1369109 (Python Code)

Max Activating Token Index: 702

Text #12

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.5286. Min Act: -0.0000

Data Index: 1605739 (Python Code)

Max Activating Token Index: 200

Text #13

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.3401. Min Act: -0.0000

Data Index: 1522462 (Python Code)

Max Activating Token Index: 658

Text #14

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.3433. Min Act: -0.0000

Data Index: 1408785 (Python Code)

Max Activating Token Index: 327

Text #15

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.4080. Min Act: -0.0000

Data Index: 1628680 (Python Code)

Max Activating Token Index: 181

Text #16

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.4753. Min Act: -0.0000

Data Index: 1511393 (Python Code)

Max Activating Token Index: 822

Text #17

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.3878. Min Act: -0.0000

Data Index: 1552103 (Python Code)

Max Activating Token Index: 795

Text #18

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.4201. Min Act: -0.0000

Data Index: 1627457 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 1.9687. Min Range: -1.9687

Max Act: 1.3242. Min Act: -0.0000

Data Index: 1479454 (Python Code)

Max Activating Token Index: 150