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

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

Neuron 1983 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0548. Min Act: -0.0001

Data Index: 765267 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0593. Min Act: -0.0001

Data Index: 414227 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0510. Min Act: -0.0001

Data Index: 1613133 (Python Code)

Max Activating Token Index: 876

Text #3

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1219136 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0486. Min Act: -0.0001

Data Index: 84488 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0480. Min Act: -0.0002

Data Index: 32330 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0481. Min Act: -0.0002

Data Index: 593820 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0479. Min Act: -0.0002

Data Index: 928856 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0484. Min Act: -0.0002

Data Index: 473700 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0471. Min Act: -0.0001

Data Index: 1635487 (Python Code)

Max Activating Token Index: 951

Text #10

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0446. Min Act: -0.0001

Data Index: 975386 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0437. Min Act: -0.0001

Data Index: 44664 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1432729 (Python Code)

Max Activating Token Index: 888

Text #13

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1147330 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0444. Min Act: -0.0001

Data Index: 626667 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0449. Min Act: -0.0001

Data Index: 724592 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1106340 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1120407 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0454. Min Act: -0.0001

Data Index: 157022 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0445. Min Act: -0.0002

Data Index: 591023 (C4 (Web Text))

Max Activating Token Index: 95