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

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

Neuron 702 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: 0.0523. Min Range: -0.0523

Max Act: 0.0521. Min Act: -0.0006

Data Index: 292373 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0513. Min Act: -0.0006

Data Index: 1650539 (Python Code)

Max Activating Token Index: 323

Text #2

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0523. Min Act: -0.0005

Data Index: 1307797 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0479. Min Act: -0.0006

Data Index: 1261703 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0489. Min Act: -0.0006

Data Index: 59968 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0496. Min Act: -0.0006

Data Index: 292881 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0491. Min Act: -0.0006

Data Index: 316812 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0476. Min Act: -0.0006

Data Index: 596254 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0481. Min Act: -0.0006

Data Index: 909012 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0469. Min Act: -0.0006

Data Index: 489032 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0466. Min Act: -0.0006

Data Index: 251611 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0467. Min Act: -0.0006

Data Index: 214689 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0477. Min Act: -0.0006

Data Index: 1339279 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0475. Min Act: -0.0006

Data Index: 1013876 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0472. Min Act: -0.0006

Data Index: 369657 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0460. Min Act: -0.0006

Data Index: 1038681 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0479. Min Act: -0.0006

Data Index: 574899 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0461. Min Act: -0.0006

Data Index: 88626 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0479. Min Act: -0.0006

Data Index: 669734 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0459. Min Act: -0.0006

Data Index: 1208829 (C4 (Web Text))

Max Activating Token Index: 419