Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4421 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.9783. Min Act: -0.0000

Data Index: 1420497 (Python Code)

Max Activating Token Index: 57

Text #1

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.8948. Min Act: -0.0000

Data Index: 1386889 (Python Code)

Max Activating Token Index: 732

Text #2

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.4918. Min Act: -0.0000

Data Index: 987201 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.4425. Min Act: -0.0000

Data Index: 994156 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.5024. Min Act: -0.0000

Data Index: 1082144 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.4792. Min Act: -0.0000

Data Index: 852891 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.5778. Min Act: -0.0000

Data Index: 1289622 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.5163. Min Act: -0.0000

Data Index: 1376736 (Python Code)

Max Activating Token Index: 360

Text #8

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.2477. Min Act: -0.0000

Data Index: 1624632 (Python Code)

Max Activating Token Index: 633

Text #9

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.2709. Min Act: -0.0000

Data Index: 1231783 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.2757. Min Act: -0.0000

Data Index: 1469776 (Python Code)

Max Activating Token Index: 402

Text #11

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.3325. Min Act: -0.0000

Data Index: 1488537 (Python Code)

Max Activating Token Index: 24

Text #12

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.2422. Min Act: -0.0000

Data Index: 1401931 (Python Code)

Max Activating Token Index: 49

Text #13

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.2949. Min Act: -0.0000

Data Index: 311585 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.3770. Min Act: -0.0000

Data Index: 1377410 (Python Code)

Max Activating Token Index: 583

Text #15

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.1452. Min Act: -0.0000

Data Index: 1508263 (Python Code)

Max Activating Token Index: 726

Text #16

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.4523. Min Act: -0.0000

Data Index: 163194 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.2630. Min Act: -0.0000

Data Index: 504591 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.3633. Min Act: -0.0000

Data Index: 1593880 (Python Code)

Max Activating Token Index: 180

Text #19

Max Range: 1.9783. Min Range: -1.9783

Max Act: 1.3559. Min Act: -0.0000

Data Index: 617922 (C4 (Web Text))

Max Activating Token Index: 453