Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1237 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0597. Min Act: -0.0002

Data Index: 872025 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0571. Min Act: -0.0001

Data Index: 572869 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1033279 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1068501 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0518. Min Act: -0.0002

Data Index: 768531 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0500. Min Act: -0.0002

Data Index: 228589 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1026429 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0500. Min Act: 0.0001

Data Index: 450671 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0489. Min Act: 0.0000

Data Index: 1094138 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0487. Min Act: -0.0002

Data Index: 636845 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1078942 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0507. Min Act: 0.0001

Data Index: 1162721 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0497. Min Act: -0.0002

Data Index: 363542 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0477. Min Act: -0.0002

Data Index: 182964 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1072524 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0457. Min Act: -0.0002

Data Index: 432928 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1061623 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1059056 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0457. Min Act: -0.0002

Data Index: 481793 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0454. Min Act: -0.0002

Data Index: 250654 (C4 (Web Text))

Max Activating Token Index: 555