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

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

Neuron 4748 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: 0.0821. Min Range: -0.0821

Max Act: 0.0821. Min Act: -0.0000

Data Index: 514785 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0653. Min Act: -0.0000

Data Index: 788459 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0552. Min Act: -0.0000

Data Index: 319094 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0526. Min Act: -0.0000

Data Index: 680672 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0565. Min Act: -0.0000

Data Index: 1346608 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0583. Min Act: -0.0000

Data Index: 226389 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0500. Min Act: -0.0000

Data Index: 559207 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0518. Min Act: -0.0000

Data Index: 895907 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0532. Min Act: -0.0000

Data Index: 335699 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0543. Min Act: -0.0000

Data Index: 619785 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0512. Min Act: -0.0000

Data Index: 282517 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0534. Min Act: -0.0000

Data Index: 987681 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0476. Min Act: -0.0000

Data Index: 1111196 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0490. Min Act: -0.0000

Data Index: 214094 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0468. Min Act: -0.0000

Data Index: 47236 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0413. Min Act: -0.0000

Data Index: 178586 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0459. Min Act: -0.0000

Data Index: 114265 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0481. Min Act: -0.0000

Data Index: 1132216 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0459. Min Act: -0.0000

Data Index: 626366 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0430. Min Act: -0.0000

Data Index: 910815 (C4 (Web Text))

Max Activating Token Index: 66