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

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

Neuron 3144 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0850. Min Act: -0.0002

Data Index: 358570 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0741. Min Act: -0.0002

Data Index: 57502 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1137488 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0613. Min Act: -0.0002

Data Index: 40974 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0602. Min Act: -0.0002

Data Index: 147984 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0555. Min Act: -0.0002

Data Index: 825994 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0571. Min Act: -0.0002

Data Index: 315500 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0495. Min Act: -0.0002

Data Index: 248047 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0622. Min Act: -0.0002

Data Index: 328091 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0483. Min Act: -0.0002

Data Index: 92996 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0519. Min Act: -0.0002

Data Index: 173500 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1081242 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1277566 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0491. Min Act: -0.0002

Data Index: 1115969 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0445. Min Act: -0.0002

Data Index: 803305 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0496. Min Act: -0.0002

Data Index: 747870 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0527. Min Act: -0.0002

Data Index: 187820 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0468. Min Act: -0.0002

Data Index: 417164 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0502. Min Act: -0.0002

Data Index: 972261 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0497. Min Act: -0.0002

Data Index: 170980 (C4 (Web Text))

Max Activating Token Index: 389