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

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

Neuron 4123 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.8239. Min Act: -0.0001

Data Index: 976044 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.7816. Min Act: -0.0001

Data Index: 177720 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.7628. Min Act: -0.0001

Data Index: 104641 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.7518. Min Act: -0.0001

Data Index: 1351338 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.7729. Min Act: -0.0001

Data Index: 234482 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6759. Min Act: -0.0001

Data Index: 184672 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6901. Min Act: -0.0001

Data Index: 148288 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6748. Min Act: -0.0001

Data Index: 660927 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6636. Min Act: -0.0001

Data Index: 172235 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5867. Min Act: -0.0001

Data Index: 696538 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6492. Min Act: -0.0001

Data Index: 1339362 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6652. Min Act: -0.0001

Data Index: 398737 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5918. Min Act: -0.0001

Data Index: 1327011 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6089. Min Act: -0.0001

Data Index: 1128174 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5717. Min Act: -0.0001

Data Index: 76419 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6045. Min Act: -0.0000

Data Index: 359986 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6728. Min Act: -0.0001

Data Index: 1353664 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5764. Min Act: -0.0001

Data Index: 161916 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5980. Min Act: -0.0001

Data Index: 794669 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6365. Min Act: -0.0001

Data Index: 46009 (C4 (Web Text))

Max Activating Token Index: 494