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

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

Neuron 175 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0536. Min Act: -0.0002

Data Index: 470289 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1249012 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0480. Min Act: -0.0002

Data Index: 388924 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0466. Min Act: -0.0002

Data Index: 644841 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0450. Min Act: -0.0002

Data Index: 635970 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0448. Min Act: -0.0002

Data Index: 780897 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0444. Min Act: -0.0002

Data Index: 759492 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0439. Min Act: -0.0002

Data Index: 437531 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0418. Min Act: -0.0002

Data Index: 888292 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1101985 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0410. Min Act: -0.0002

Data Index: 46133 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0410. Min Act: -0.0002

Data Index: 164904 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0408. Min Act: -0.0002

Data Index: 4853 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0382. Min Act: -0.0002

Data Index: 844813 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0388. Min Act: -0.0002

Data Index: 942900 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0380. Min Act: -0.0002

Data Index: 200346 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1006789 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0382. Min Act: -0.0002

Data Index: 707427 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0382. Min Act: -0.0002

Data Index: 143263 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0382. Min Act: -0.0002

Data Index: 749138 (C4 (Web Text))

Max Activating Token Index: 115