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

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

Neuron 620 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0613. Min Act: -0.0001

Data Index: 976036 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0608. Min Act: -0.0001

Data Index: 584976 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0555. Min Act: -0.0001

Data Index: 379098 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0517. Min Act: -0.0001

Data Index: 433496 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0516. Min Act: -0.0001

Data Index: 208349 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0499. Min Act: -0.0001

Data Index: 610137 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0531. Min Act: -0.0001

Data Index: 754912 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0540. Min Act: -0.0001

Data Index: 874467 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0544. Min Act: -0.0001

Data Index: 57796 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1083110 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0504. Min Act: -0.0001

Data Index: 342534 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0485. Min Act: -0.0001

Data Index: 810879 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0473. Min Act: -0.0001

Data Index: 1273351 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0470. Min Act: -0.0001

Data Index: 236558 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0461. Min Act: -0.0001

Data Index: 1086544 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0469. Min Act: -0.0001

Data Index: 984600 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1139070 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0421. Min Act: -0.0001

Data Index: 256299 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0464. Min Act: -0.0001

Data Index: 928008 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0439. Min Act: -0.0001

Data Index: 1321002 (C4 (Web Text))

Max Activating Token Index: 563