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

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

Neuron 5048 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1840. Min Act: -0.0000

Data Index: 142020 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1725. Min Act: -0.0000

Data Index: 1590984 (Python Code)

Max Activating Token Index: 32

Text #2

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1775. Min Act: -0.0000

Data Index: 547199 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1708. Min Act: -0.0000

Data Index: 792231 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1554715 (Python Code)

Max Activating Token Index: 947

Text #5

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1617. Min Act: -0.0000

Data Index: 547170 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1511. Min Act: -0.0000

Data Index: 1547870 (Python Code)

Max Activating Token Index: 51

Text #7

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1593690 (Python Code)

Max Activating Token Index: 749

Text #8

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1385. Min Act: -0.0000

Data Index: 162603 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1331. Min Act: -0.0000

Data Index: 954823 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1461. Min Act: -0.0000

Data Index: 1109444 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1440. Min Act: -0.0000

Data Index: 727696 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1082518 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1287. Min Act: -0.0000

Data Index: 339858 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1298. Min Act: -0.0000

Data Index: 1560048 (Python Code)

Max Activating Token Index: 367

Text #15

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1366353 (Python Code)

Max Activating Token Index: 193

Text #16

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1362. Min Act: -0.0000

Data Index: 711677 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1215. Min Act: -0.0000

Data Index: 784784 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1341. Min Act: -0.0000

Data Index: 589438 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1326. Min Act: -0.0000

Data Index: 193028 (C4 (Web Text))

Max Activating Token Index: 599