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

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

Neuron 5578 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1372. Min Range: -2.1372

Max Act: 2.1372. Min Act: -0.0000

Data Index: 770292 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.9368. Min Act: -0.0000

Data Index: 1103726 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.8014. Min Act: -0.0000

Data Index: 1259803 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.8006. Min Act: -0.0000

Data Index: 1280728 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.7326. Min Act: -0.0000

Data Index: 347835 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.6678. Min Act: -0.0000

Data Index: 523798 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.6577. Min Act: -0.0000

Data Index: 644705 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.7345. Min Act: -0.0000

Data Index: 484495 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.6576. Min Act: -0.0000

Data Index: 1264010 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.5382. Min Act: -0.0000

Data Index: 1149638 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.7135. Min Act: -0.0000

Data Index: 705856 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.5114. Min Act: -0.0000

Data Index: 858453 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.5053. Min Act: -0.0000

Data Index: 357472 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.4960. Min Act: -0.0000

Data Index: 328592 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.4847. Min Act: -0.0000

Data Index: 1580301 (Python Code)

Max Activating Token Index: 19

Text #15

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.4792. Min Act: -0.0000

Data Index: 221409 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.1889. Min Act: -0.0000

Data Index: 997630 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.5584. Min Act: -0.0000

Data Index: 603046 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.4740. Min Act: -0.0000

Data Index: 473419 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 2.1372. Min Range: -2.1372

Max Act: 1.4479. Min Act: -0.0000

Data Index: 375600 (C4 (Web Text))

Max Activating Token Index: 991