Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3858 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.7380. Min Act: -0.0000

Data Index: 278579 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.6331. Min Act: -0.0000

Data Index: 753313 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.6495. Min Act: -0.0000

Data Index: 754109 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.5991. Min Act: -0.0000

Data Index: 391120 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.5560. Min Act: -0.0000

Data Index: 183317 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.5721. Min Act: -0.0000

Data Index: 239717 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1102585 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1151807 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.5382. Min Act: -0.0000

Data Index: 969983 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1295366 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.5240. Min Act: -0.0000

Data Index: 342877 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.5132. Min Act: -0.0000

Data Index: 702430 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.5238. Min Act: -0.0000

Data Index: 774309 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.4844. Min Act: -0.0000

Data Index: 1114943 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.5396. Min Act: -0.0000

Data Index: 843204 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1213562 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.4402. Min Act: -0.0000

Data Index: 777298 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1111509 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.4663. Min Act: -0.0000

Data Index: 86140 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1314922 (C4 (Web Text))

Max Activating Token Index: 29