Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1656 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 7.2292. Min Range: -7.2292

Max Act: 7.1843. Min Act: -0.0001

Data Index: 1609712 (Python Code)

Max Activating Token Index: 169

Text #1

Max Range: 7.2292. Min Range: -7.2292

Max Act: 7.2292. Min Act: -0.0001

Data Index: 1554910 (Python Code)

Max Activating Token Index: 447

Text #2

Max Range: 7.2292. Min Range: -7.2292

Max Act: 6.9208. Min Act: -0.0001

Data Index: 1628764 (Python Code)

Max Activating Token Index: 730

Text #3

Max Range: 7.2292. Min Range: -7.2292

Max Act: 6.5840. Min Act: -0.0000

Data Index: 1370799 (Python Code)

Max Activating Token Index: 493

Text #4

Max Range: 7.2292. Min Range: -7.2292

Max Act: 6.1761. Min Act: -0.0000

Data Index: 1516738 (Python Code)

Max Activating Token Index: 224

Text #5

Max Range: 7.2292. Min Range: -7.2292

Max Act: 6.8251. Min Act: -0.0000

Data Index: 1639560 (Python Code)

Max Activating Token Index: 762

Text #6

Max Range: 7.2292. Min Range: -7.2292

Max Act: 6.5259. Min Act: -0.0001

Data Index: 1643295 (Python Code)

Max Activating Token Index: 123

Text #7

Max Range: 7.2292. Min Range: -7.2292

Max Act: 6.1844. Min Act: -0.0000

Data Index: 1367640 (Python Code)

Max Activating Token Index: 556

Text #8

Max Range: 7.2292. Min Range: -7.2292

Max Act: 6.4837. Min Act: -0.0001

Data Index: 1411304 (Python Code)

Max Activating Token Index: 720

Text #9

Max Range: 7.2292. Min Range: -7.2292

Max Act: 6.1643. Min Act: -0.0001

Data Index: 1635451 (Python Code)

Max Activating Token Index: 226

Text #10

Max Range: 7.2292. Min Range: -7.2292

Max Act: 6.0952. Min Act: -0.0001

Data Index: 1388274 (Python Code)

Max Activating Token Index: 315

Text #11

Max Range: 7.2292. Min Range: -7.2292

Max Act: 6.0573. Min Act: -0.0000

Data Index: 1642770 (Python Code)

Max Activating Token Index: 177

Text #12

Max Range: 7.2292. Min Range: -7.2292

Max Act: 6.0667. Min Act: -0.0001

Data Index: 1550867 (Python Code)

Max Activating Token Index: 594

Text #13

Max Range: 7.2292. Min Range: -7.2292

Max Act: 6.2888. Min Act: -0.0000

Data Index: 1474365 (Python Code)

Max Activating Token Index: 178

Text #14

Max Range: 7.2292. Min Range: -7.2292

Max Act: 6.1005. Min Act: -0.0001

Data Index: 1425585 (Python Code)

Max Activating Token Index: 208

Text #15

Max Range: 7.2292. Min Range: -7.2292

Max Act: 6.0845. Min Act: -0.0001

Data Index: 1370625 (Python Code)

Max Activating Token Index: 179

Text #16

Max Range: 7.2292. Min Range: -7.2292

Max Act: 5.9300. Min Act: -0.0001

Data Index: 1546272 (Python Code)

Max Activating Token Index: 213

Text #17

Max Range: 7.2292. Min Range: -7.2292

Max Act: 6.2142. Min Act: -0.0001

Data Index: 1528573 (Python Code)

Max Activating Token Index: 1013

Text #18

Max Range: 7.2292. Min Range: -7.2292

Max Act: 6.0318. Min Act: -0.0001

Data Index: 1557270 (Python Code)

Max Activating Token Index: 937

Text #19

Max Range: 7.2292. Min Range: -7.2292

Max Act: 5.7945. Min Act: -0.0000

Data Index: 1547810 (Python Code)

Max Activating Token Index: 140