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

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

Neuron 1300 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.4458. Min Act: -0.0000

Data Index: 1623503 (Python Code)

Max Activating Token Index: 639

Text #1

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.3687. Min Act: -0.0000

Data Index: 1549911 (Python Code)

Max Activating Token Index: 159

Text #2

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.2872. Min Act: -0.0000

Data Index: 1382658 (Python Code)

Max Activating Token Index: 346

Text #3

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.2077. Min Act: -0.0000

Data Index: 1502601 (Python Code)

Max Activating Token Index: 96

Text #4

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.3538. Min Act: -0.0000

Data Index: 1498448 (Python Code)

Max Activating Token Index: 179

Text #5

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.2684. Min Act: 0.0000

Data Index: 1599440 (Python Code)

Max Activating Token Index: 819

Text #6

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.1221. Min Act: -0.0000

Data Index: 1458482 (Python Code)

Max Activating Token Index: 892

Text #7

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.2438. Min Act: -0.0000

Data Index: 1460995 (Python Code)

Max Activating Token Index: 495

Text #8

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.3419. Min Act: -0.0000

Data Index: 1375103 (Python Code)

Max Activating Token Index: 882

Text #9

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.3161. Min Act: -0.0000

Data Index: 1558725 (Python Code)

Max Activating Token Index: 218

Text #10

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.1950. Min Act: -0.0000

Data Index: 1644920 (Python Code)

Max Activating Token Index: 879

Text #11

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.1126. Min Act: -0.0000

Data Index: 1594311 (Python Code)

Max Activating Token Index: 339

Text #12

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.1591. Min Act: -0.0000

Data Index: 1508842 (Python Code)

Max Activating Token Index: 596

Text #13

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.1680. Min Act: -0.0000

Data Index: 1371733 (Python Code)

Max Activating Token Index: 607

Text #14

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.2268. Min Act: -0.0000

Data Index: 1555918 (Python Code)

Max Activating Token Index: 229

Text #15

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.1526. Min Act: -0.0000

Data Index: 1496115 (Python Code)

Max Activating Token Index: 207

Text #16

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.0997. Min Act: -0.0000

Data Index: 1485907 (Python Code)

Max Activating Token Index: 385

Text #17

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.2171. Min Act: -0.0000

Data Index: 1498581 (Python Code)

Max Activating Token Index: 496

Text #18

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.0373. Min Act: -0.0000

Data Index: 1623015 (Python Code)

Max Activating Token Index: 170

Text #19

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.0866. Min Act: -0.0000

Data Index: 1571586 (Python Code)

Max Activating Token Index: 882