Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 625 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.9844. Min Act: -0.0001

Data Index: 1437211 (Python Code)

Max Activating Token Index: 1016

Text #1

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.8923. Min Act: -0.0001

Data Index: 1617469 (Python Code)

Max Activating Token Index: 807

Text #2

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.9072. Min Act: -0.0001

Data Index: 1572865 (Python Code)

Max Activating Token Index: 1019

Text #3

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.9287. Min Act: -0.0001

Data Index: 1396428 (Python Code)

Max Activating Token Index: 1022

Text #4

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.9296. Min Act: -0.0001

Data Index: 1396742 (Python Code)

Max Activating Token Index: 916

Text #5

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.9143. Min Act: -0.0001

Data Index: 1527129 (Python Code)

Max Activating Token Index: 985

Text #6

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.8821. Min Act: -0.0001

Data Index: 1374640 (Python Code)

Max Activating Token Index: 1002

Text #7

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.9298. Min Act: -0.0001

Data Index: 1437151 (Python Code)

Max Activating Token Index: 992

Text #8

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.9271. Min Act: -0.0001

Data Index: 1550764 (Python Code)

Max Activating Token Index: 1008

Text #9

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.8889. Min Act: -0.0001

Data Index: 1586437 (Python Code)

Max Activating Token Index: 1020

Text #10

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.9273. Min Act: -0.0001

Data Index: 1532042 (Python Code)

Max Activating Token Index: 935

Text #11

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.8977. Min Act: -0.0001

Data Index: 1552178 (Python Code)

Max Activating Token Index: 23

Text #12

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.8689. Min Act: -0.0001

Data Index: 1469965 (Python Code)

Max Activating Token Index: 1021

Text #13

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.8664. Min Act: -0.0001

Data Index: 1378938 (Python Code)

Max Activating Token Index: 1017

Text #14

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.8880. Min Act: -0.0001

Data Index: 1587396 (Python Code)

Max Activating Token Index: 1005

Text #15

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.8811. Min Act: -0.0001

Data Index: 1394297 (Python Code)

Max Activating Token Index: 1013

Text #16

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.8578. Min Act: -0.0001

Data Index: 1576784 (Python Code)

Max Activating Token Index: 992

Text #17

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.8266. Min Act: -0.0001

Data Index: 1385899 (Python Code)

Max Activating Token Index: 993

Text #18

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.8589. Min Act: -0.0001

Data Index: 1534537 (Python Code)

Max Activating Token Index: 1015

Text #19

Max Range: 0.9844. Min Range: -0.9844

Max Act: 0.9073. Min Act: -0.0001

Data Index: 1645508 (Python Code)

Max Activating Token Index: 1020