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

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

Neuron 1634 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: 3.8852. Min Range: -3.8852

Max Act: 3.8852. Min Act: -0.0000

Data Index: 1491431 (Python Code)

Max Activating Token Index: 949

Text #1

Max Range: 3.8852. Min Range: -3.8852

Max Act: 3.2934. Min Act: -0.0000

Data Index: 1503320 (Python Code)

Max Activating Token Index: 394

Text #2

Max Range: 3.8852. Min Range: -3.8852

Max Act: 3.2713. Min Act: -0.0000

Data Index: 1553929 (Python Code)

Max Activating Token Index: 651

Text #3

Max Range: 3.8852. Min Range: -3.8852

Max Act: 3.2534. Min Act: -0.0000

Data Index: 1562897 (Python Code)

Max Activating Token Index: 52

Text #4

Max Range: 3.8852. Min Range: -3.8852

Max Act: 3.2588. Min Act: -0.0000

Data Index: 1603625 (Python Code)

Max Activating Token Index: 250

Text #5

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.9454. Min Act: -0.0000

Data Index: 1617291 (Python Code)

Max Activating Token Index: 30

Text #6

Max Range: 3.8852. Min Range: -3.8852

Max Act: 3.0382. Min Act: -0.0000

Data Index: 1547404 (Python Code)

Max Activating Token Index: 321

Text #7

Max Range: 3.8852. Min Range: -3.8852

Max Act: 3.0213. Min Act: -0.0000

Data Index: 1528172 (Python Code)

Max Activating Token Index: 97

Text #8

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.8345. Min Act: -0.0000

Data Index: 1404653 (Python Code)

Max Activating Token Index: 889

Text #9

Max Range: 3.8852. Min Range: -3.8852

Max Act: 3.1304. Min Act: -0.0000

Data Index: 1434633 (Python Code)

Max Activating Token Index: 964

Text #10

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.7092. Min Act: -0.0000

Data Index: 1124117 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.9544. Min Act: -0.0000

Data Index: 1574403 (Python Code)

Max Activating Token Index: 405

Text #12

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.8905. Min Act: -0.0000

Data Index: 1400009 (Python Code)

Max Activating Token Index: 97

Text #13

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.8604. Min Act: -0.0000

Data Index: 1405474 (Python Code)

Max Activating Token Index: 276

Text #14

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.8340. Min Act: -0.0000

Data Index: 506528 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.7123. Min Act: -0.0000

Data Index: 777109 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.8318. Min Act: -0.0000

Data Index: 782394 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.8241. Min Act: -0.0000

Data Index: 1450206 (Python Code)

Max Activating Token Index: 182

Text #18

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.8251. Min Act: -0.0000

Data Index: 1528109 (Python Code)

Max Activating Token Index: 995

Text #19

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.6745. Min Act: -0.0000

Data Index: 857298 (C4 (Web Text))

Max Activating Token Index: 175