Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1172 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0695. Min Act: -0.0002

Data Index: 411018 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1508858 (Python Code)

Max Activating Token Index: 99

Text #2

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0574. Min Act: -0.0002

Data Index: 584633 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1173071 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0564. Min Act: -0.0001

Data Index: 817279 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0555. Min Act: -0.0002

Data Index: 665172 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1572483 (Python Code)

Max Activating Token Index: 782

Text #7

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1467578 (Python Code)

Max Activating Token Index: 462

Text #8

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0507. Min Act: -0.0002

Data Index: 393773 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0533. Min Act: -0.0002

Data Index: 468088 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0499. Min Act: -0.0001

Data Index: 155839 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0493. Min Act: -0.0002

Data Index: 46578 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1524951 (Python Code)

Max Activating Token Index: 608

Text #13

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0548. Min Act: -0.0002

Data Index: 241680 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0481. Min Act: -0.0001

Data Index: 1110444 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0479. Min Act: -0.0002

Data Index: 243584 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1490346 (Python Code)

Max Activating Token Index: 901

Text #17

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1499324 (Python Code)

Max Activating Token Index: 522

Text #18

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1652840 (Python Code)

Max Activating Token Index: 797

Text #19

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0434. Min Act: -0.0002

Data Index: 365888 (C4 (Web Text))

Max Activating Token Index: 894