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

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

Neuron 5094 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: 0.0723. Min Range: -0.0723

Max Act: 0.0723. Min Act: -0.0001

Data Index: 272265 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0632. Min Act: -0.0001

Data Index: 499714 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0618. Min Act: -0.0001

Data Index: 95327 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0506. Min Act: -0.0001

Data Index: 1050104 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0540. Min Act: -0.0001

Data Index: 397773 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1089621 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0516. Min Act: -0.0001

Data Index: 622640 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0527. Min Act: -0.0001

Data Index: 343311 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0492. Min Act: -0.0001

Data Index: 980796 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0493. Min Act: -0.0001

Data Index: 858921 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1088595 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0440. Min Act: -0.0001

Data Index: 443082 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1167661 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1032252 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1169489 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0424. Min Act: -0.0001

Data Index: 730152 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0445. Min Act: -0.0001

Data Index: 1195402 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0444. Min Act: -0.0002

Data Index: 856735 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0361. Min Act: -0.0001

Data Index: 484733 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0376. Min Act: -0.0001

Data Index: 846494 (C4 (Web Text))

Max Activating Token Index: 270