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

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

Neuron 5985 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: 0.0790. Min Range: -0.0790

Max Act: 0.0790. Min Act: -0.0002

Data Index: 256057 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0602. Min Act: -0.0002

Data Index: 769016 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1025883 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1263127 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1157618 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0532. Min Act: -0.0002

Data Index: 961127 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1121863 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0511. Min Act: -0.0002

Data Index: 362656 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0499. Min Act: -0.0002

Data Index: 912657 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1185493 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0492. Min Act: -0.0002

Data Index: 118749 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1010972 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0463. Min Act: -0.0002

Data Index: 185043 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1135298 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0479. Min Act: -0.0002

Data Index: 240153 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0464. Min Act: -0.0002

Data Index: 792147 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1307911 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1311809 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1087853 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1096435 (C4 (Web Text))

Max Activating Token Index: 646