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

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

Neuron 4875 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1611. Min Act: -0.0000

Data Index: 1459235 (Python Code)

Max Activating Token Index: 956

Text #1

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1416. Min Act: -0.0000

Data Index: 1585925 (Python Code)

Max Activating Token Index: 339

Text #2

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1448. Min Act: -0.0000

Data Index: 1540614 (Python Code)

Max Activating Token Index: 81

Text #3

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1457. Min Act: -0.0000

Data Index: 1411398 (Python Code)

Max Activating Token Index: 763

Text #4

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1472. Min Act: -0.0000

Data Index: 1461110 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1459316 (Python Code)

Max Activating Token Index: 996

Text #6

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1456844 (Python Code)

Max Activating Token Index: 1021

Text #7

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1413. Min Act: -0.0000

Data Index: 1515266 (Python Code)

Max Activating Token Index: 1013

Text #8

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1398958 (Python Code)

Max Activating Token Index: 729

Text #9

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1372. Min Act: -0.0000

Data Index: 1431177 (Python Code)

Max Activating Token Index: 241

Text #10

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1268. Min Act: -0.0000

Data Index: 1640200 (Python Code)

Max Activating Token Index: 416

Text #11

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1536888 (Python Code)

Max Activating Token Index: 203

Text #12

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1388534 (Python Code)

Max Activating Token Index: 695

Text #13

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1215. Min Act: -0.0000

Data Index: 1610230 (Python Code)

Max Activating Token Index: 813

Text #14

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1242. Min Act: -0.0000

Data Index: 1649558 (Python Code)

Max Activating Token Index: 738

Text #15

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1235. Min Act: -0.0000

Data Index: 1542865 (Python Code)

Max Activating Token Index: 976

Text #16

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1629331 (Python Code)

Max Activating Token Index: 343

Text #17

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1228. Min Act: -0.0000

Data Index: 1616987 (Python Code)

Max Activating Token Index: 23

Text #18

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1530287 (Python Code)

Max Activating Token Index: 299

Text #19

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1170. Min Act: -0.0000

Data Index: 1445936 (Python Code)

Max Activating Token Index: 539