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

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

Neuron 4011 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: 1.9996. Min Range: -1.9996

Max Act: 1.9467. Min Act: -0.0000

Data Index: 1576897 (Python Code)

Max Activating Token Index: 628

Text #1

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.8363. Min Act: -0.0000

Data Index: 1630710 (Python Code)

Max Activating Token Index: 955

Text #2

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.7813. Min Act: -0.0000

Data Index: 1607348 (Python Code)

Max Activating Token Index: 435

Text #3

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.9996. Min Act: -0.0000

Data Index: 1546338 (Python Code)

Max Activating Token Index: 974

Text #4

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.8463. Min Act: -0.0000

Data Index: 1418686 (Python Code)

Max Activating Token Index: 799

Text #5

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.7192. Min Act: -0.0000

Data Index: 1614253 (Python Code)

Max Activating Token Index: 622

Text #6

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.8103. Min Act: -0.0000

Data Index: 1501092 (Python Code)

Max Activating Token Index: 372

Text #7

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.7275. Min Act: -0.0000

Data Index: 1564313 (Python Code)

Max Activating Token Index: 914

Text #8

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.7337. Min Act: -0.0000

Data Index: 1585904 (Python Code)

Max Activating Token Index: 126

Text #9

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.7122. Min Act: -0.0000

Data Index: 1418943 (Python Code)

Max Activating Token Index: 237

Text #10

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.6712. Min Act: -0.0000

Data Index: 1621160 (Python Code)

Max Activating Token Index: 851

Text #11

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.6546. Min Act: -0.0000

Data Index: 1467755 (Python Code)

Max Activating Token Index: 137

Text #12

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.6259. Min Act: -0.0000

Data Index: 1495241 (Python Code)

Max Activating Token Index: 251

Text #13

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.6324. Min Act: -0.0000

Data Index: 1524767 (Python Code)

Max Activating Token Index: 662

Text #14

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.6350. Min Act: -0.0000

Data Index: 1376665 (Python Code)

Max Activating Token Index: 245

Text #15

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.7250. Min Act: -0.0000

Data Index: 1511006 (Python Code)

Max Activating Token Index: 877

Text #16

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.6388. Min Act: -0.0000

Data Index: 1549164 (Python Code)

Max Activating Token Index: 804

Text #17

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.5142. Min Act: -0.0000

Data Index: 1396574 (Python Code)

Max Activating Token Index: 383

Text #18

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.5973. Min Act: -0.0000

Data Index: 1586262 (Python Code)

Max Activating Token Index: 142

Text #19

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.5992. Min Act: -0.0000

Data Index: 1546624 (Python Code)

Max Activating Token Index: 924