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

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

Neuron 894 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.3870. Min Act: -0.0001

Data Index: 1511467 (Python Code)

Max Activating Token Index: 261

Text #1

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.3871. Min Act: -0.0000

Data Index: 1537413 (Python Code)

Max Activating Token Index: 625

Text #2

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.4216. Min Act: -0.0001

Data Index: 1502890 (Python Code)

Max Activating Token Index: 303

Text #3

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.3013. Min Act: -0.0000

Data Index: 1436448 (Python Code)

Max Activating Token Index: 286

Text #4

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.2530. Min Act: -0.0001

Data Index: 1423522 (Python Code)

Max Activating Token Index: 901

Text #5

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.1987. Min Act: -0.0001

Data Index: 1401843 (Python Code)

Max Activating Token Index: 736

Text #6

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.2044. Min Act: -0.0000

Data Index: 1475234 (Python Code)

Max Activating Token Index: 675

Text #7

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.2019. Min Act: -0.0000

Data Index: 1397553 (Python Code)

Max Activating Token Index: 616

Text #8

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.3067. Min Act: -0.0000

Data Index: 1589476 (Python Code)

Max Activating Token Index: 201

Text #9

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.2453. Min Act: -0.0000

Data Index: 1471080 (Python Code)

Max Activating Token Index: 486

Text #10

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.2335. Min Act: -0.0000

Data Index: 1525804 (Python Code)

Max Activating Token Index: 199

Text #11

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.2028. Min Act: -0.0000

Data Index: 1597480 (Python Code)

Max Activating Token Index: 635

Text #12

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.2958. Min Act: -0.0000

Data Index: 1429587 (Python Code)

Max Activating Token Index: 114

Text #13

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.2165. Min Act: -0.0001

Data Index: 1411723 (Python Code)

Max Activating Token Index: 478

Text #14

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.1911. Min Act: -0.0001

Data Index: 1425565 (Python Code)

Max Activating Token Index: 347

Text #15

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.2054. Min Act: -0.0001

Data Index: 1651620 (Python Code)

Max Activating Token Index: 422

Text #16

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.2116. Min Act: -0.0000

Data Index: 1389232 (Python Code)

Max Activating Token Index: 14

Text #17

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.1630. Min Act: -0.0000

Data Index: 1403970 (Python Code)

Max Activating Token Index: 244

Text #18

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.2358. Min Act: -0.0001

Data Index: 1583674 (Python Code)

Max Activating Token Index: 774

Text #19

Max Range: 1.4216. Min Range: -1.4216

Max Act: 1.2001. Min Act: -0.0001

Data Index: 1372224 (Python Code)

Max Activating Token Index: 548