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

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

Neuron 1993 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0577. Min Act: -0.0001

Data Index: 843970 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0515. Min Act: -0.0001

Data Index: 601198 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0484. Min Act: -0.0001

Data Index: 721030 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0539. Min Act: -0.0001

Data Index: 644529 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0463. Min Act: -0.0001

Data Index: 408274 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0488. Min Act: -0.0001

Data Index: 835555 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0487. Min Act: -0.0001

Data Index: 4201 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1208368 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0512. Min Act: -0.0001

Data Index: 446463 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0482. Min Act: -0.0001

Data Index: 602273 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0521. Min Act: -0.0001

Data Index: 1163751 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1093820 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0452. Min Act: -0.0001

Data Index: 284371 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0471. Min Act: -0.0001

Data Index: 424903 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0507. Min Act: -0.0001

Data Index: 972495 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0476. Min Act: -0.0002

Data Index: 215546 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0486. Min Act: -0.0002

Data Index: 711724 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0490. Min Act: -0.0001

Data Index: 142695 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0500. Min Act: -0.0001

Data Index: 238826 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0493. Min Act: -0.0002

Data Index: 288986 (C4 (Web Text))

Max Activating Token Index: 535