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

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

Neuron 4785 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: 2.6408. Min Range: -2.6408

Max Act: 2.6408. Min Act: -0.0000

Data Index: 1541396 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.4674. Min Act: -0.0000

Data Index: 1503165 (Python Code)

Max Activating Token Index: 7

Text #2

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.4674. Min Act: -0.0000

Data Index: 1379848 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.4674. Min Act: -0.0000

Data Index: 1559812 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.4674. Min Act: -0.0000

Data Index: 1546980 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.3155. Min Act: -0.0000

Data Index: 1390103 (Python Code)

Max Activating Token Index: 955

Text #6

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.4390. Min Act: -0.0000

Data Index: 1390237 (Python Code)

Max Activating Token Index: 920

Text #7

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.4549. Min Act: -0.0001

Data Index: 1534065 (Python Code)

Max Activating Token Index: 942

Text #8

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.3902. Min Act: -0.0000

Data Index: 1586868 (Python Code)

Max Activating Token Index: 976

Text #9

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.1378. Min Act: -0.0000

Data Index: 1573943 (Python Code)

Max Activating Token Index: 943

Text #10

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.4908. Min Act: -0.0000

Data Index: 1531813 (Python Code)

Max Activating Token Index: 33

Text #11

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.2119. Min Act: -0.0000

Data Index: 1555910 (Python Code)

Max Activating Token Index: 18

Text #12

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.2118. Min Act: -0.0000

Data Index: 1391850 (Python Code)

Max Activating Token Index: 865

Text #13

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.2246. Min Act: -0.0000

Data Index: 1528821 (Python Code)

Max Activating Token Index: 969

Text #14

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.1957. Min Act: -0.0000

Data Index: 1618729 (Python Code)

Max Activating Token Index: 841

Text #15

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.1823. Min Act: -0.0001

Data Index: 1458782 (Python Code)

Max Activating Token Index: 1004

Text #16

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.1250. Min Act: -0.0000

Data Index: 1418452 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.2299. Min Act: -0.0000

Data Index: 1436618 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.1278. Min Act: -0.0001

Data Index: 1536583 (Python Code)

Max Activating Token Index: 973

Text #19

Max Range: 2.6408. Min Range: -2.6408

Max Act: 2.2009. Min Act: -0.0000

Data Index: 1478860 (Python Code)

Max Activating Token Index: 927