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

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

Neuron 5008 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.8329. Min Act: -0.0000

Data Index: 324765 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.8395. Min Act: -0.0000

Data Index: 675497 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.7534. Min Act: -0.0000

Data Index: 320036 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.7111. Min Act: -0.0000

Data Index: 1477748 (Python Code)

Max Activating Token Index: 27

Text #4

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1277546 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6914. Min Act: -0.0000

Data Index: 333602 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6496. Min Act: -0.0000

Data Index: 1373099 (Python Code)

Max Activating Token Index: 164

Text #7

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1244810 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.5907. Min Act: -0.0000

Data Index: 526933 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6534. Min Act: -0.0000

Data Index: 879451 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6449. Min Act: -0.0000

Data Index: 997308 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6121. Min Act: -0.0000

Data Index: 252863 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6567. Min Act: -0.0000

Data Index: 264027 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1142995 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1370085 (Python Code)

Max Activating Token Index: 20

Text #15

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.5806. Min Act: -0.0000

Data Index: 915760 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1223890 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6292. Min Act: -0.0000

Data Index: 1377781 (Python Code)

Max Activating Token Index: 113

Text #18

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1181955 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6466. Min Act: -0.0000

Data Index: 579680 (C4 (Web Text))

Max Activating Token Index: 974