Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1312 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2164. Min Act: -0.0000

Data Index: 555224 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2240. Min Act: -0.0001

Data Index: 859443 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1989. Min Act: -0.0001

Data Index: 346170 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2005. Min Act: -0.0001

Data Index: 933998 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1995. Min Act: -0.0000

Data Index: 261867 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1919. Min Act: -0.0000

Data Index: 956795 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1793. Min Act: -0.0001

Data Index: 755991 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1843. Min Act: -0.0001

Data Index: 302563 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1849. Min Act: -0.0001

Data Index: 233332 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1947. Min Act: -0.0000

Data Index: 544144 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1827. Min Act: -0.0001

Data Index: 930883 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1644. Min Act: -0.0001

Data Index: 195670 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1672. Min Act: -0.0001

Data Index: 568414 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1635. Min Act: -0.0000

Data Index: 18774 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1319982 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1588. Min Act: -0.0001

Data Index: 1317204 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1518. Min Act: -0.0001

Data Index: 183743 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1449. Min Act: -0.0000

Data Index: 661176 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1443. Min Act: -0.0000

Data Index: 491317 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1535. Min Act: -0.0001

Data Index: 641623 (C4 (Web Text))

Max Activating Token Index: 496