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

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

Neuron 3366 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.6376. Min Act: -0.0000

Data Index: 279192 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1488948 (Python Code)

Max Activating Token Index: 976

Text #2

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5728. Min Act: -0.0000

Data Index: 346318 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1263041 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5654. Min Act: -0.0000

Data Index: 602490 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5210. Min Act: -0.0000

Data Index: 1128160 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5532. Min Act: -0.0000

Data Index: 472245 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5321. Min Act: -0.0000

Data Index: 240801 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1603244 (Python Code)

Max Activating Token Index: 575

Text #9

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1217688 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1307523 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5297. Min Act: -0.0000

Data Index: 4742 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5069. Min Act: -0.0000

Data Index: 1563619 (Python Code)

Max Activating Token Index: 208

Text #13

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5209. Min Act: -0.0000

Data Index: 781219 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5061. Min Act: -0.0000

Data Index: 657967 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1342292 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4847. Min Act: -0.0000

Data Index: 995249 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4941. Min Act: -0.0000

Data Index: 325333 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4800. Min Act: -0.0000

Data Index: 974833 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4901. Min Act: -0.0000

Data Index: 1128832 (C4 (Web Text))

Max Activating Token Index: 372