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

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

Neuron 2563 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.9417. Min Act: -0.0000

Data Index: 955724 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.8118. Min Act: -0.0000

Data Index: 1349640 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.8632. Min Act: -0.0000

Data Index: 203091 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.8248. Min Act: -0.0000

Data Index: 935374 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.8150. Min Act: -0.0000

Data Index: 992567 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.7340. Min Act: -0.0000

Data Index: 1042691 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.7265. Min Act: -0.0000

Data Index: 701292 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.7113. Min Act: 0.0000

Data Index: 1310643 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.6853. Min Act: -0.0000

Data Index: 339036 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.6716. Min Act: -0.0000

Data Index: 525870 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.6591. Min Act: -0.0000

Data Index: 779279 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.6319. Min Act: 0.0001

Data Index: 794941 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.6483. Min Act: -0.0000

Data Index: 618318 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.6420. Min Act: -0.0000

Data Index: 494235 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.6239. Min Act: -0.0000

Data Index: 12610 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.6234. Min Act: -0.0000

Data Index: 718588 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.6307. Min Act: 0.0001

Data Index: 980326 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.6253. Min Act: -0.0000

Data Index: 331815 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.6035. Min Act: 0.0001

Data Index: 1133523 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.9417. Min Range: -0.9417

Max Act: 0.5978. Min Act: -0.0000

Data Index: 217069 (C4 (Web Text))

Max Activating Token Index: 45