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

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

Neuron 968 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.7283. Min Act: -0.0000

Data Index: 1584200 (Python Code)

Max Activating Token Index: 361

Text #1

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.8017. Min Act: -0.0000

Data Index: 1390989 (Python Code)

Max Activating Token Index: 458

Text #2

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.5664. Min Act: -0.0000

Data Index: 1481929 (Python Code)

Max Activating Token Index: 489

Text #3

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.4681. Min Act: -0.0000

Data Index: 1501423 (Python Code)

Max Activating Token Index: 902

Text #4

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.3760. Min Act: -0.0000

Data Index: 223309 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.4090. Min Act: -0.0000

Data Index: 1565072 (Python Code)

Max Activating Token Index: 975

Text #6

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1623785 (Python Code)

Max Activating Token Index: 310

Text #7

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.2287. Min Act: -0.0000

Data Index: 1369691 (Python Code)

Max Activating Token Index: 978

Text #8

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.3048. Min Act: -0.0000

Data Index: 1637083 (Python Code)

Max Activating Token Index: 286

Text #9

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.2911. Min Act: -0.0000

Data Index: 1422465 (Python Code)

Max Activating Token Index: 561

Text #10

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.2916. Min Act: -0.0000

Data Index: 1473187 (Python Code)

Max Activating Token Index: 979

Text #11

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.2798. Min Act: -0.0000

Data Index: 1648096 (Python Code)

Max Activating Token Index: 940

Text #12

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.3821. Min Act: 0.0000

Data Index: 1406030 (Python Code)

Max Activating Token Index: 70

Text #13

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.2096. Min Act: -0.0000

Data Index: 1591435 (Python Code)

Max Activating Token Index: 690

Text #14

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.1927. Min Act: -0.0000

Data Index: 1642315 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.1806. Min Act: -0.0000

Data Index: 1604707 (Python Code)

Max Activating Token Index: 370

Text #16

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.4025. Min Act: -0.0000

Data Index: 1421357 (Python Code)

Max Activating Token Index: 949

Text #17

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.2286. Min Act: -0.0000

Data Index: 1611239 (Python Code)

Max Activating Token Index: 612

Text #18

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.1918. Min Act: -0.0000

Data Index: 1396750 (Python Code)

Max Activating Token Index: 985

Text #19

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.2132. Min Act: -0.0000

Data Index: 1439208 (Python Code)

Max Activating Token Index: 830