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

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

Neuron 1580 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: 3.6967. Min Range: -3.6967

Max Act: 3.6967. Min Act: -0.0001

Data Index: 1539335 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.5715. Min Act: -0.0000

Data Index: 1592487 (Python Code)

Max Activating Token Index: 21

Text #2

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.1233. Min Act: -0.0001

Data Index: 1417476 (Python Code)

Max Activating Token Index: 602

Text #3

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.2805. Min Act: -0.0001

Data Index: 1537926 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.0446. Min Act: -0.0001

Data Index: 1557840 (Python Code)

Max Activating Token Index: 45

Text #5

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.1849. Min Act: -0.0001

Data Index: 1504888 (Python Code)

Max Activating Token Index: 141

Text #6

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.1442. Min Act: -0.0001

Data Index: 1541679 (Python Code)

Max Activating Token Index: 33

Text #7

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.1798. Min Act: -0.0001

Data Index: 1475470 (Python Code)

Max Activating Token Index: 378

Text #8

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.1412. Min Act: -0.0001

Data Index: 1438473 (Python Code)

Max Activating Token Index: 672

Text #9

Max Range: 3.6967. Min Range: -3.6967

Max Act: 2.9910. Min Act: -0.0001

Data Index: 1519489 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 3.6967. Min Range: -3.6967

Max Act: 2.9929. Min Act: -0.0001

Data Index: 1634234 (Python Code)

Max Activating Token Index: 12

Text #11

Max Range: 3.6967. Min Range: -3.6967

Max Act: 2.9270. Min Act: -0.0001

Data Index: 1583294 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 3.6967. Min Range: -3.6967

Max Act: 2.9076. Min Act: -0.0001

Data Index: 1644945 (Python Code)

Max Activating Token Index: 23

Text #13

Max Range: 3.6967. Min Range: -3.6967

Max Act: 2.8843. Min Act: -0.0001

Data Index: 1517645 (Python Code)

Max Activating Token Index: 78

Text #14

Max Range: 3.6967. Min Range: -3.6967

Max Act: 2.8868. Min Act: -0.0001

Data Index: 1373126 (Python Code)

Max Activating Token Index: 21

Text #15

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.0045. Min Act: -0.0001

Data Index: 1568567 (Python Code)

Max Activating Token Index: 29

Text #16

Max Range: 3.6967. Min Range: -3.6967

Max Act: 2.6909. Min Act: -0.0001

Data Index: 1410138 (Python Code)

Max Activating Token Index: 90

Text #17

Max Range: 3.6967. Min Range: -3.6967

Max Act: 2.8375. Min Act: -0.0001

Data Index: 1621999 (Python Code)

Max Activating Token Index: 501

Text #18

Max Range: 3.6967. Min Range: -3.6967

Max Act: 2.6685. Min Act: -0.0001

Data Index: 1432218 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 3.6967. Min Range: -3.6967

Max Act: 2.9238. Min Act: -0.0001

Data Index: 1504050 (Python Code)

Max Activating Token Index: 819