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

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

Neuron 3873 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: 0.0936. Min Range: -0.0936

Max Act: 0.0936. Min Act: -0.0001

Data Index: 639894 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0824. Min Act: -0.0001

Data Index: 1101943 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0761. Min Act: -0.0001

Data Index: 395406 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0700. Min Act: -0.0001

Data Index: 804907 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0633. Min Act: -0.0001

Data Index: 13647 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0555. Min Act: -0.0001

Data Index: 1052511 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1280146 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0538. Min Act: -0.0001

Data Index: 149933 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0530. Min Act: -0.0001

Data Index: 709093 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0548. Min Act: -0.0001

Data Index: 991532 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1108394 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0516. Min Act: -0.0001

Data Index: 443970 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0485. Min Act: -0.0001

Data Index: 7056 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1193792 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0506. Min Act: -0.0001

Data Index: 803494 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0488. Min Act: -0.0001

Data Index: 549763 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0488. Min Act: -0.0001

Data Index: 853649 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0478. Min Act: -0.0001

Data Index: 358235 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0462. Min Act: -0.0001

Data Index: 888152 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0492. Min Act: -0.0001

Data Index: 302066 (C4 (Web Text))

Max Activating Token Index: 396