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

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

Neuron 1232 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3382. Min Range: -2.3382

Max Act: 2.3382. Min Act: -0.0000

Data Index: 1411495 (Python Code)

Max Activating Token Index: 814

Text #1

Max Range: 2.3382. Min Range: -2.3382

Max Act: 2.3184. Min Act: -0.0000

Data Index: 1653895 (Python Code)

Max Activating Token Index: 898

Text #2

Max Range: 2.3382. Min Range: -2.3382

Max Act: 2.0773. Min Act: -0.0000

Data Index: 1537067 (Python Code)

Max Activating Token Index: 472

Text #3

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.7637. Min Act: -0.0000

Data Index: 1469854 (Python Code)

Max Activating Token Index: 213

Text #4

Max Range: 2.3382. Min Range: -2.3382

Max Act: 2.1250. Min Act: -0.0000

Data Index: 257611 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 2.3382. Min Range: -2.3382

Max Act: 2.0410. Min Act: -0.0000

Data Index: 970171 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 2.3382. Min Range: -2.3382

Max Act: 2.0166. Min Act: -0.0000

Data Index: 1387162 (Python Code)

Max Activating Token Index: 581

Text #7

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.9518. Min Act: -0.0000

Data Index: 1482783 (Python Code)

Max Activating Token Index: 55

Text #8

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.9867. Min Act: -0.0000

Data Index: 1382153 (Python Code)

Max Activating Token Index: 859

Text #9

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.9345. Min Act: -0.0000

Data Index: 1372881 (Python Code)

Max Activating Token Index: 886

Text #10

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.9874. Min Act: -0.0000

Data Index: 260400 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.8027. Min Act: -0.0000

Data Index: 1419781 (Python Code)

Max Activating Token Index: 721

Text #12

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.7894. Min Act: -0.0000

Data Index: 1583892 (Python Code)

Max Activating Token Index: 194

Text #13

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.7832. Min Act: -0.0000

Data Index: 1552900 (Python Code)

Max Activating Token Index: 239

Text #14

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.8124. Min Act: -0.0000

Data Index: 1629597 (Python Code)

Max Activating Token Index: 121

Text #15

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.7383. Min Act: -0.0000

Data Index: 1387801 (Python Code)

Max Activating Token Index: 339

Text #16

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.8637. Min Act: -0.0000

Data Index: 1606450 (Python Code)

Max Activating Token Index: 381

Text #17

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.8201. Min Act: -0.0000

Data Index: 1449378 (Python Code)

Max Activating Token Index: 329

Text #18

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.8275. Min Act: -0.0000

Data Index: 1624133 (Python Code)

Max Activating Token Index: 241

Text #19

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.8349. Min Act: -0.0000

Data Index: 1455391 (Python Code)

Max Activating Token Index: 144