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

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

Neuron 5534 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1512113 (Python Code)

Max Activating Token Index: 393

Text #1

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1453989 (Python Code)

Max Activating Token Index: 741

Text #2

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1040203 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1427793 (Python Code)

Max Activating Token Index: 534

Text #4

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1629892 (Python Code)

Max Activating Token Index: 465

Text #5

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1406692 (Python Code)

Max Activating Token Index: 291

Text #6

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0269. Min Act: -0.0002

Data Index: 752627 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1369122 (Python Code)

Max Activating Token Index: 846

Text #8

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1615034 (Python Code)

Max Activating Token Index: 58

Text #9

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1033408 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0258. Min Act: -0.0002

Data Index: 910585 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1413960 (Python Code)

Max Activating Token Index: 274

Text #12

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0257. Min Act: -0.0002

Data Index: 815074 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0248. Min Act: -0.0002

Data Index: 942282 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0255. Min Act: -0.0002

Data Index: 579148 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0244. Min Act: -0.0002

Data Index: 234119 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1561095 (Python Code)

Max Activating Token Index: 193

Text #17

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0247. Min Act: -0.0002

Data Index: 510378 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0239. Min Act: -0.0002

Data Index: 869350 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1507839 (Python Code)

Max Activating Token Index: 541