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

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

Neuron 4444 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0588. Min Act: -0.0000

Data Index: 250164 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0544. Min Act: -0.0000

Data Index: 769651 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0501. Min Act: -0.0000

Data Index: 1548012 (Python Code)

Max Activating Token Index: 357

Text #3

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1652239 (Python Code)

Max Activating Token Index: 790

Text #4

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0521. Min Act: -0.0000

Data Index: 980163 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0520. Min Act: -0.0000

Data Index: 379788 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0528. Min Act: -0.0000

Data Index: 883520 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0489. Min Act: -0.0000

Data Index: 544825 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0493. Min Act: -0.0000

Data Index: 781897 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0473. Min Act: -0.0000

Data Index: 859316 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0487. Min Act: -0.0000

Data Index: 432769 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0518. Min Act: -0.0000

Data Index: 1275999 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0467. Min Act: -0.0000

Data Index: 1067683 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0497. Min Act: -0.0000

Data Index: 696111 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0491. Min Act: -0.0000

Data Index: 603448 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0455. Min Act: -0.0000

Data Index: 353401 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0452. Min Act: -0.0000

Data Index: 145220 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0418. Min Act: -0.0000

Data Index: 779401 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0426. Min Act: -0.0000

Data Index: 237709 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0454. Min Act: -0.0000

Data Index: 1109699 (C4 (Web Text))

Max Activating Token Index: 423