Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1009 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.7333. Min Act: -0.0001

Data Index: 1562084 (Python Code)

Max Activating Token Index: 503

Text #1

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.3377. Min Act: -0.0001

Data Index: 1639578 (Python Code)

Max Activating Token Index: 736

Text #2

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.3337. Min Act: -0.0000

Data Index: 1446967 (Python Code)

Max Activating Token Index: 645

Text #3

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.1753. Min Act: -0.0000

Data Index: 1604062 (Python Code)

Max Activating Token Index: 516

Text #4

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.1204. Min Act: -0.0001

Data Index: 1454237 (Python Code)

Max Activating Token Index: 727

Text #5

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.1308. Min Act: -0.0000

Data Index: 1638428 (Python Code)

Max Activating Token Index: 699

Text #6

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.1569. Min Act: -0.0001

Data Index: 1452730 (Python Code)

Max Activating Token Index: 583

Text #7

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.1870. Min Act: -0.0000

Data Index: 1418838 (Python Code)

Max Activating Token Index: 862

Text #8

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.1235. Min Act: -0.0000

Data Index: 1578043 (Python Code)

Max Activating Token Index: 518

Text #9

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.1103. Min Act: -0.0001

Data Index: 1651725 (Python Code)

Max Activating Token Index: 93

Text #10

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.1366. Min Act: -0.0001

Data Index: 1651352 (Python Code)

Max Activating Token Index: 943

Text #11

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.0684. Min Act: -0.0000

Data Index: 1487670 (Python Code)

Max Activating Token Index: 573

Text #12

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.0903. Min Act: -0.0001

Data Index: 1448260 (Python Code)

Max Activating Token Index: 842

Text #13

Max Range: 1.7333. Min Range: -1.7333

Max Act: 0.9540. Min Act: -0.0000

Data Index: 1504852 (Python Code)

Max Activating Token Index: 680

Text #14

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.1085. Min Act: -0.0000

Data Index: 1582238 (Python Code)

Max Activating Token Index: 934

Text #15

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.0417. Min Act: -0.0001

Data Index: 1649246 (Python Code)

Max Activating Token Index: 170

Text #16

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.0414. Min Act: 0.0001

Data Index: 1495420 (Python Code)

Max Activating Token Index: 924

Text #17

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.0323. Min Act: -0.0001

Data Index: 1499272 (Python Code)

Max Activating Token Index: 889

Text #18

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.0693. Min Act: -0.0001

Data Index: 1565444 (Python Code)

Max Activating Token Index: 260

Text #19

Max Range: 1.7333. Min Range: -1.7333

Max Act: 1.0624. Min Act: -0.0000

Data Index: 1469372 (Python Code)

Max Activating Token Index: 646