Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 190 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0643. Min Act: -0.0006

Data Index: 375387 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0643. Min Act: -0.0006

Data Index: 1286017 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0603. Min Act: -0.0005

Data Index: 917162 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0564. Min Act: -0.0006

Data Index: 108306 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0538. Min Act: -0.0006

Data Index: 383154 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0538. Min Act: -0.0006

Data Index: 480081 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0531. Min Act: -0.0006

Data Index: 242910 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0529. Min Act: -0.0005

Data Index: 202420 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0528. Min Act: -0.0005

Data Index: 252517 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0522. Min Act: -0.0005

Data Index: 1218668 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0537. Min Act: -0.0006

Data Index: 655093 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0499. Min Act: -0.0006

Data Index: 828295 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0496. Min Act: -0.0006

Data Index: 378066 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0497. Min Act: -0.0006

Data Index: 860094 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0537. Min Act: -0.0006

Data Index: 912584 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0513. Min Act: -0.0006

Data Index: 431590 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0509. Min Act: -0.0006

Data Index: 781819 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0506. Min Act: -0.0005

Data Index: 1118980 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0481. Min Act: -0.0006

Data Index: 1051907 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0501. Min Act: -0.0006

Data Index: 230043 (C4 (Web Text))

Max Activating Token Index: 480