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

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

Neuron 4464 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1080. Min Act: -0.0000

Data Index: 657235 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1424945 (Python Code)

Max Activating Token Index: 174

Text #2

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0947. Min Act: -0.0000

Data Index: 432083 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0896. Min Act: -0.0000

Data Index: 1592527 (Python Code)

Max Activating Token Index: 410

Text #4

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0851. Min Act: -0.0000

Data Index: 1411024 (Python Code)

Max Activating Token Index: 466

Text #5

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0777. Min Act: -0.0000

Data Index: 633228 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0839. Min Act: -0.0000

Data Index: 461800 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1631224 (Python Code)

Max Activating Token Index: 61

Text #8

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0869. Min Act: -0.0000

Data Index: 592304 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0813. Min Act: -0.0000

Data Index: 1376626 (Python Code)

Max Activating Token Index: 181

Text #10

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0808. Min Act: -0.0000

Data Index: 1502275 (Python Code)

Max Activating Token Index: 784

Text #11

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0841. Min Act: -0.0000

Data Index: 1364397 (Python Code)

Max Activating Token Index: 702

Text #12

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0818. Min Act: -0.0000

Data Index: 1244310 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0817. Min Act: -0.0000

Data Index: 1363553 (Python Code)

Max Activating Token Index: 192

Text #14

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0807. Min Act: -0.0000

Data Index: 1105537 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0770. Min Act: -0.0000

Data Index: 1587092 (Python Code)

Max Activating Token Index: 882

Text #16

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0817. Min Act: -0.0000

Data Index: 598049 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1621846 (Python Code)

Max Activating Token Index: 264

Text #18

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0792. Min Act: -0.0000

Data Index: 1492285 (Python Code)

Max Activating Token Index: 115

Text #19

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0749. Min Act: -0.0000

Data Index: 1629227 (Python Code)

Max Activating Token Index: 919