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

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

Neuron 552 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0574. Min Act: -0.0002

Data Index: 276774 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0567. Min Act: -0.0002

Data Index: 736077 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0571. Min Act: -0.0002

Data Index: 775516 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0535. Min Act: -0.0002

Data Index: 191139 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0527. Min Act: -0.0002

Data Index: 107740 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1651165 (Python Code)

Max Activating Token Index: 113

Text #6

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0541. Min Act: -0.0002

Data Index: 153496 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1139209 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0500. Min Act: -0.0002

Data Index: 902447 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0482. Min Act: -0.0002

Data Index: 808235 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1403898 (Python Code)

Max Activating Token Index: 476

Text #11

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1033488 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1073718 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1153625 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0467. Min Act: -0.0002

Data Index: 619008 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0486. Min Act: -0.0002

Data Index: 737143 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0496. Min Act: -0.0002

Data Index: 581593 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1005279 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0459. Min Act: -0.0002

Data Index: 315603 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1423978 (Python Code)

Max Activating Token Index: 655