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

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

Neuron 5070 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0553. Min Range: -3.0553

Max Act: 3.0074. Min Act: -0.0000

Data Index: 1475865 (Python Code)

Max Activating Token Index: 118

Text #1

Max Range: 3.0553. Min Range: -3.0553

Max Act: 3.0553. Min Act: -0.0000

Data Index: 1428203 (Python Code)

Max Activating Token Index: 1019

Text #2

Max Range: 3.0553. Min Range: -3.0553

Max Act: 2.2803. Min Act: -0.0000

Data Index: 1473788 (Python Code)

Max Activating Token Index: 362

Text #3

Max Range: 3.0553. Min Range: -3.0553

Max Act: 2.2434. Min Act: -0.0000

Data Index: 1632234 (Python Code)

Max Activating Token Index: 212

Text #4

Max Range: 3.0553. Min Range: -3.0553

Max Act: 2.5444. Min Act: -0.0000

Data Index: 1629490 (Python Code)

Max Activating Token Index: 637

Text #5

Max Range: 3.0553. Min Range: -3.0553

Max Act: 2.4957. Min Act: -0.0001

Data Index: 1021468 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 3.0553. Min Range: -3.0553

Max Act: 2.2156. Min Act: -0.0000

Data Index: 1386797 (Python Code)

Max Activating Token Index: 814

Text #7

Max Range: 3.0553. Min Range: -3.0553

Max Act: 2.5244. Min Act: -0.0001

Data Index: 1596169 (Python Code)

Max Activating Token Index: 394

Text #8

Max Range: 3.0553. Min Range: -3.0553

Max Act: 2.2464. Min Act: -0.0001

Data Index: 1557808 (Python Code)

Max Activating Token Index: 95

Text #9

Max Range: 3.0553. Min Range: -3.0553

Max Act: 1.9759. Min Act: -0.0000

Data Index: 1475092 (Python Code)

Max Activating Token Index: 218

Text #10

Max Range: 3.0553. Min Range: -3.0553

Max Act: 2.1756. Min Act: -0.0000

Data Index: 1513285 (Python Code)

Max Activating Token Index: 341

Text #11

Max Range: 3.0553. Min Range: -3.0553

Max Act: 2.0571. Min Act: -0.0000

Data Index: 1589013 (Python Code)

Max Activating Token Index: 612

Text #12

Max Range: 3.0553. Min Range: -3.0553

Max Act: 2.4163. Min Act: -0.0000

Data Index: 1447473 (Python Code)

Max Activating Token Index: 741

Text #13

Max Range: 3.0553. Min Range: -3.0553

Max Act: 2.1351. Min Act: -0.0000

Data Index: 1582404 (Python Code)

Max Activating Token Index: 716

Text #14

Max Range: 3.0553. Min Range: -3.0553

Max Act: 2.1259. Min Act: -0.0000

Data Index: 1418643 (Python Code)

Max Activating Token Index: 45

Text #15

Max Range: 3.0553. Min Range: -3.0553

Max Act: 2.3378. Min Act: -0.0001

Data Index: 1607131 (Python Code)

Max Activating Token Index: 752

Text #16

Max Range: 3.0553. Min Range: -3.0553

Max Act: 2.2214. Min Act: -0.0000

Data Index: 1365144 (Python Code)

Max Activating Token Index: 103

Text #17

Max Range: 3.0553. Min Range: -3.0553

Max Act: 1.8438. Min Act: -0.0000

Data Index: 1475056 (Python Code)

Max Activating Token Index: 314

Text #18

Max Range: 3.0553. Min Range: -3.0553

Max Act: 2.0549. Min Act: -0.0000

Data Index: 1533913 (Python Code)

Max Activating Token Index: 49

Text #19

Max Range: 3.0553. Min Range: -3.0553

Max Act: 1.8214. Min Act: -0.0000

Data Index: 1547129 (Python Code)

Max Activating Token Index: 679