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

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

Neuron 3086 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.2027. Min Act: -0.0001

Data Index: 1461061 (Python Code)

Max Activating Token Index: 999

Text #1

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.2124. Min Act: -0.0001

Data Index: 1617171 (Python Code)

Max Activating Token Index: 346

Text #2

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1890. Min Act: -0.0002

Data Index: 628681 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1975. Min Act: -0.0001

Data Index: 1436104 (Python Code)

Max Activating Token Index: 949

Text #4

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.2043. Min Act: -0.0001

Data Index: 1462219 (Python Code)

Max Activating Token Index: 964

Text #5

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1954. Min Act: -0.0001

Data Index: 1533853 (Python Code)

Max Activating Token Index: 445

Text #6

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1387. Min Act: -0.0002

Data Index: 249024 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1950. Min Act: -0.0002

Data Index: 800742 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1415. Min Act: -0.0002

Data Index: 1239956 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1956. Min Act: -0.0001

Data Index: 1559303 (Python Code)

Max Activating Token Index: 842

Text #10

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1914. Min Act: -0.0001

Data Index: 1459438 (Python Code)

Max Activating Token Index: 947

Text #11

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1833. Min Act: -0.0001

Data Index: 1626555 (Python Code)

Max Activating Token Index: 512

Text #12

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1733. Min Act: -0.0001

Data Index: 1522813 (Python Code)

Max Activating Token Index: 799

Text #13

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1830. Min Act: -0.0001

Data Index: 1455185 (Python Code)

Max Activating Token Index: 518

Text #14

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1716. Min Act: -0.0001

Data Index: 1655188 (Python Code)

Max Activating Token Index: 454

Text #15

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1569. Min Act: -0.0002

Data Index: 1116022 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1685. Min Act: -0.0002

Data Index: 738755 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1663. Min Act: -0.0002

Data Index: 1103590 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1609. Min Act: -0.0001

Data Index: 527420 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1699. Min Act: -0.0001

Data Index: 897162 (C4 (Web Text))

Max Activating Token Index: 588