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

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

Neuron 1383 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1611. Min Range: -4.1611

Max Act: 4.1611. Min Act: -0.0001

Data Index: 451224 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 4.1611. Min Range: -4.1611

Max Act: 4.0137. Min Act: -0.0001

Data Index: 987349 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 4.1611. Min Range: -4.1611

Max Act: 3.8297. Min Act: -0.0001

Data Index: 726932 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 4.1611. Min Range: -4.1611

Max Act: 3.9740. Min Act: -0.0001

Data Index: 1104454 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 4.1611. Min Range: -4.1611

Max Act: 3.8582. Min Act: -0.0001

Data Index: 1260360 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 4.1611. Min Range: -4.1611

Max Act: 4.0058. Min Act: -0.0001

Data Index: 1332312 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 4.1611. Min Range: -4.1611

Max Act: 3.8611. Min Act: -0.0001

Data Index: 164086 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 4.1611. Min Range: -4.1611

Max Act: 3.7108. Min Act: -0.0001

Data Index: 210235 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 4.1611. Min Range: -4.1611

Max Act: 3.8425. Min Act: -0.0001

Data Index: 396618 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 4.1611. Min Range: -4.1611

Max Act: 3.8467. Min Act: -0.0001

Data Index: 1277851 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 4.1611. Min Range: -4.1611

Max Act: 4.1289. Min Act: -0.0001

Data Index: 451902 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 4.1611. Min Range: -4.1611

Max Act: 3.8722. Min Act: -0.0001

Data Index: 706796 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 4.1611. Min Range: -4.1611

Max Act: 3.8448. Min Act: -0.0001

Data Index: 338836 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 4.1611. Min Range: -4.1611

Max Act: 3.8625. Min Act: -0.0001

Data Index: 642254 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 4.1611. Min Range: -4.1611

Max Act: 3.8480. Min Act: -0.0001

Data Index: 527633 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 4.1611. Min Range: -4.1611

Max Act: 3.9965. Min Act: -0.0001

Data Index: 717427 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 4.1611. Min Range: -4.1611

Max Act: 3.8577. Min Act: -0.0001

Data Index: 1280657 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 4.1611. Min Range: -4.1611

Max Act: 3.8714. Min Act: -0.0001

Data Index: 182869 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 4.1611. Min Range: -4.1611

Max Act: 3.6425. Min Act: -0.0001

Data Index: 384197 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 4.1611. Min Range: -4.1611

Max Act: 3.5131. Min Act: -0.0001

Data Index: 1004919 (C4 (Web Text))

Max Activating Token Index: 955