Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 545 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0468. Min Act: -0.0001

Data Index: 443122 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0388. Min Act: -0.0001

Data Index: 103261 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0440. Min Act: -0.0001

Data Index: 365266 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0452. Min Act: -0.0001

Data Index: 165053 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0417. Min Act: -0.0001

Data Index: 54498 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1310353 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0431. Min Act: -0.0001

Data Index: 635442 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0396. Min Act: -0.0001

Data Index: 1269990 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1063254 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0411. Min Act: -0.0001

Data Index: 767810 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0422. Min Act: -0.0001

Data Index: 900906 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0425. Min Act: -0.0001

Data Index: 351762 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0441. Min Act: -0.0001

Data Index: 555088 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0420. Min Act: -0.0001

Data Index: 110871 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0394. Min Act: -0.0001

Data Index: 1318620 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0404. Min Act: -0.0001

Data Index: 882271 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0424. Min Act: -0.0001

Data Index: 829314 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0400. Min Act: -0.0001

Data Index: 100961 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0425. Min Act: -0.0001

Data Index: 826051 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0396. Min Act: -0.0001

Data Index: 800929 (C4 (Web Text))

Max Activating Token Index: 929