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

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

Neuron 4211 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.6739. Min Act: -0.0000

Data Index: 751269 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1496186 (Python Code)

Max Activating Token Index: 998

Text #2

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1464662 (Python Code)

Max Activating Token Index: 686

Text #3

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1630941 (Python Code)

Max Activating Token Index: 679

Text #4

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1607495 (Python Code)

Max Activating Token Index: 740

Text #5

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1493216 (Python Code)

Max Activating Token Index: 229

Text #6

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1468161 (Python Code)

Max Activating Token Index: 72

Text #7

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1531631 (Python Code)

Max Activating Token Index: 630

Text #8

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1382697 (Python Code)

Max Activating Token Index: 814

Text #9

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4948. Min Act: -0.0000

Data Index: 1643238 (Python Code)

Max Activating Token Index: 312

Text #10

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1524961 (Python Code)

Max Activating Token Index: 947

Text #11

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1547281 (Python Code)

Max Activating Token Index: 664

Text #12

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1603920 (Python Code)

Max Activating Token Index: 753

Text #13

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1626954 (Python Code)

Max Activating Token Index: 876

Text #14

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1654549 (Python Code)

Max Activating Token Index: 1019

Text #15

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1654124 (Python Code)

Max Activating Token Index: 19

Text #16

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1533724 (Python Code)

Max Activating Token Index: 783

Text #17

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1373490 (Python Code)

Max Activating Token Index: 700

Text #18

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1389290 (Python Code)

Max Activating Token Index: 979

Text #19

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4912. Min Act: -0.0000

Data Index: 1557761 (Python Code)

Max Activating Token Index: 150