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

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

Neuron 4493 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4223. Min Range: -5.4223

Max Act: 4.9506. Min Act: -0.0000

Data Index: 100816 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 5.4223. Min Range: -5.4223

Max Act: 5.2402. Min Act: -0.0000

Data Index: 344024 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 5.4223. Min Range: -5.4223

Max Act: 5.4223. Min Act: -0.0000

Data Index: 463213 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 5.4223. Min Range: -5.4223

Max Act: 5.1290. Min Act: -0.0000

Data Index: 897397 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 5.4223. Min Range: -5.4223

Max Act: 5.1260. Min Act: -0.0000

Data Index: 471393 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 5.4223. Min Range: -5.4223

Max Act: 4.9265. Min Act: -0.0000

Data Index: 1019954 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 5.4223. Min Range: -5.4223

Max Act: 5.0656. Min Act: -0.0000

Data Index: 278565 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 5.4223. Min Range: -5.4223

Max Act: 5.0549. Min Act: -0.0001

Data Index: 141064 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 5.4223. Min Range: -5.4223

Max Act: 5.0043. Min Act: -0.0000

Data Index: 532724 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 5.4223. Min Range: -5.4223

Max Act: 4.9368. Min Act: -0.0000

Data Index: 834076 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 5.4223. Min Range: -5.4223

Max Act: 4.7460. Min Act: -0.0000

Data Index: 17254 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 5.4223. Min Range: -5.4223

Max Act: 4.9231. Min Act: -0.0000

Data Index: 577000 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 5.4223. Min Range: -5.4223

Max Act: 5.1074. Min Act: -0.0000

Data Index: 954810 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 5.4223. Min Range: -5.4223

Max Act: 5.0728. Min Act: -0.0000

Data Index: 100275 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 5.4223. Min Range: -5.4223

Max Act: 5.2487. Min Act: -0.0000

Data Index: 1102810 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 5.4223. Min Range: -5.4223

Max Act: 4.8673. Min Act: -0.0000

Data Index: 196700 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 5.4223. Min Range: -5.4223

Max Act: 4.9127. Min Act: -0.0000

Data Index: 1221367 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 5.4223. Min Range: -5.4223

Max Act: 4.5407. Min Act: -0.0000

Data Index: 828169 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 5.4223. Min Range: -5.4223

Max Act: 4.6216. Min Act: -0.0000

Data Index: 670236 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 5.4223. Min Range: -5.4223

Max Act: 4.5846. Min Act: -0.0000

Data Index: 91384 (C4 (Web Text))

Max Activating Token Index: 551