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

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

Neuron 2614 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0395. Min Act: -0.0001

Data Index: 936731 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0417. Min Act: -0.0001

Data Index: 778957 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0389. Min Act: -0.0000

Data Index: 1088728 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0382. Min Act: -0.0001

Data Index: 374092 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0347. Min Act: -0.0000

Data Index: 791127 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0370. Min Act: -0.0001

Data Index: 835956 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0365. Min Act: -0.0000

Data Index: 1202840 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0363. Min Act: -0.0001

Data Index: 362701 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0347. Min Act: -0.0000

Data Index: 1163703 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0342. Min Act: -0.0001

Data Index: 43554 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0326. Min Act: -0.0001

Data Index: 718358 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0341. Min Act: -0.0000

Data Index: 296949 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0322. Min Act: -0.0001

Data Index: 587125 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0342. Min Act: -0.0000

Data Index: 237173 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1391420 (Python Code)

Max Activating Token Index: 292

Text #15

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0320. Min Act: -0.0000

Data Index: 284576 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0305. Min Act: -0.0000

Data Index: 134396 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0316. Min Act: -0.0001

Data Index: 1500516 (Python Code)

Max Activating Token Index: 357

Text #18

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1591634 (Python Code)

Max Activating Token Index: 526

Text #19

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0304. Min Act: -0.0000

Data Index: 295060 (C4 (Web Text))

Max Activating Token Index: 303