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

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

Neuron 1400 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5257. Min Range: -5.5257

Max Act: 5.5257. Min Act: -0.0000

Data Index: 1496600 (Python Code)

Max Activating Token Index: 181

Text #1

Max Range: 5.5257. Min Range: -5.5257

Max Act: 5.2293. Min Act: -0.0000

Data Index: 1470728 (Python Code)

Max Activating Token Index: 493

Text #2

Max Range: 5.5257. Min Range: -5.5257

Max Act: 5.3841. Min Act: -0.0000

Data Index: 1497509 (Python Code)

Max Activating Token Index: 919

Text #3

Max Range: 5.5257. Min Range: -5.5257

Max Act: 4.9744. Min Act: -0.0000

Data Index: 1394139 (Python Code)

Max Activating Token Index: 882

Text #4

Max Range: 5.5257. Min Range: -5.5257

Max Act: 4.6120. Min Act: -0.0000

Data Index: 1091457 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 5.5257. Min Range: -5.5257

Max Act: 4.6972. Min Act: -0.0000

Data Index: 1498033 (Python Code)

Max Activating Token Index: 699

Text #6

Max Range: 5.5257. Min Range: -5.5257

Max Act: 4.5045. Min Act: -0.0000

Data Index: 1383951 (Python Code)

Max Activating Token Index: 83

Text #7

Max Range: 5.5257. Min Range: -5.5257

Max Act: 4.4398. Min Act: -0.0000

Data Index: 1440301 (Python Code)

Max Activating Token Index: 607

Text #8

Max Range: 5.5257. Min Range: -5.5257

Max Act: 4.3381. Min Act: -0.0000

Data Index: 1451348 (Python Code)

Max Activating Token Index: 395

Text #9

Max Range: 5.5257. Min Range: -5.5257

Max Act: 4.3355. Min Act: -0.0000

Data Index: 1387282 (Python Code)

Max Activating Token Index: 526

Text #10

Max Range: 5.5257. Min Range: -5.5257

Max Act: 4.3339. Min Act: -0.0000

Data Index: 1480300 (Python Code)

Max Activating Token Index: 312

Text #11

Max Range: 5.5257. Min Range: -5.5257

Max Act: 4.1007. Min Act: -0.0000

Data Index: 1561372 (Python Code)

Max Activating Token Index: 666

Text #12

Max Range: 5.5257. Min Range: -5.5257

Max Act: 4.2809. Min Act: -0.0000

Data Index: 1368197 (Python Code)

Max Activating Token Index: 517

Text #13

Max Range: 5.5257. Min Range: -5.5257

Max Act: 3.6584. Min Act: -0.0000

Data Index: 1470434 (Python Code)

Max Activating Token Index: 307

Text #14

Max Range: 5.5257. Min Range: -5.5257

Max Act: 4.0682. Min Act: -0.0000

Data Index: 1610374 (Python Code)

Max Activating Token Index: 899

Text #15

Max Range: 5.5257. Min Range: -5.5257

Max Act: 3.9913. Min Act: -0.0000

Data Index: 1613708 (Python Code)

Max Activating Token Index: 639

Text #16

Max Range: 5.5257. Min Range: -5.5257

Max Act: 4.2998. Min Act: -0.0000

Data Index: 1529944 (Python Code)

Max Activating Token Index: 43

Text #17

Max Range: 5.5257. Min Range: -5.5257

Max Act: 3.8526. Min Act: -0.0000

Data Index: 1490453 (Python Code)

Max Activating Token Index: 331

Text #18

Max Range: 5.5257. Min Range: -5.5257

Max Act: 4.1442. Min Act: -0.0000

Data Index: 1404599 (Python Code)

Max Activating Token Index: 772

Text #19

Max Range: 5.5257. Min Range: -5.5257

Max Act: 3.8072. Min Act: -0.0000

Data Index: 1616595 (Python Code)

Max Activating Token Index: 121