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

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

Neuron 3310 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0529. Min Act: -0.0000

Data Index: 618633 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0504. Min Act: -0.0000

Data Index: 10547 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0497. Min Act: -0.0000

Data Index: 1304722 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0543. Min Act: -0.0000

Data Index: 164484 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0520. Min Act: -0.0000

Data Index: 307372 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0505. Min Act: -0.0000

Data Index: 817182 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0517. Min Act: -0.0000

Data Index: 124725 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0503. Min Act: -0.0000

Data Index: 963000 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0474. Min Act: 0.0000

Data Index: 80691 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0462. Min Act: -0.0000

Data Index: 1044425 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0465. Min Act: -0.0000

Data Index: 318198 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0490. Min Act: -0.0000

Data Index: 691857 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0439. Min Act: -0.0000

Data Index: 412195 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0471. Min Act: -0.0000

Data Index: 109223 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0468. Min Act: 0.0000

Data Index: 811499 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0431. Min Act: -0.0000

Data Index: 1278501 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0480. Min Act: -0.0000

Data Index: 1260677 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0464. Min Act: -0.0000

Data Index: 1189810 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0455. Min Act: -0.0000

Data Index: 248045 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0440. Min Act: -0.0000

Data Index: 61441 (C4 (Web Text))

Max Activating Token Index: 252