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

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

Neuron 4231 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: 2.8363. Min Range: -2.8363

Max Act: 2.8363. Min Act: -0.0000

Data Index: 1621066 (Python Code)

Max Activating Token Index: 713

Text #1

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.5296. Min Act: -0.0000

Data Index: 1549199 (Python Code)

Max Activating Token Index: 475

Text #2

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.5962. Min Act: -0.0000

Data Index: 1522281 (Python Code)

Max Activating Token Index: 735

Text #3

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.0206. Min Act: -0.0000

Data Index: 1362239 (Python Code)

Max Activating Token Index: 890

Text #4

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.9811. Min Act: -0.0000

Data Index: 1384429 (Python Code)

Max Activating Token Index: 594

Text #5

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.5926. Min Act: -0.0000

Data Index: 1433931 (Python Code)

Max Activating Token Index: 138

Text #6

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.8361. Min Act: -0.0000

Data Index: 1397370 (Python Code)

Max Activating Token Index: 852

Text #7

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.5512. Min Act: -0.0000

Data Index: 1516007 (Python Code)

Max Activating Token Index: 299

Text #8

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.4510. Min Act: -0.0000

Data Index: 1445147 (Python Code)

Max Activating Token Index: 121

Text #9

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.2724. Min Act: -0.0000

Data Index: 1461492 (Python Code)

Max Activating Token Index: 856

Text #10

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.3403. Min Act: -0.0000

Data Index: 1513398 (Python Code)

Max Activating Token Index: 763

Text #11

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.5186. Min Act: -0.0000

Data Index: 303861 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.5888. Min Act: -0.0000

Data Index: 1450753 (Python Code)

Max Activating Token Index: 771

Text #13

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.3049. Min Act: -0.0000

Data Index: 1468390 (Python Code)

Max Activating Token Index: 383

Text #14

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.3649. Min Act: -0.0000

Data Index: 1582517 (Python Code)

Max Activating Token Index: 459

Text #15

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.4224. Min Act: -0.0000

Data Index: 1388816 (Python Code)

Max Activating Token Index: 746

Text #16

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.4300. Min Act: -0.0000

Data Index: 1592748 (Python Code)

Max Activating Token Index: 574

Text #17

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.1534. Min Act: -0.0000

Data Index: 1493243 (Python Code)

Max Activating Token Index: 347

Text #18

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.2095. Min Act: -0.0000

Data Index: 1471802 (Python Code)

Max Activating Token Index: 964

Text #19

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.3504. Min Act: -0.0000

Data Index: 1432037 (Python Code)

Max Activating Token Index: 760