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

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

Neuron 670 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.8496. Min Act: -0.0001

Data Index: 701608 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.8070. Min Act: -0.0001

Data Index: 1284780 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.8290. Min Act: -0.0001

Data Index: 920757 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.8413. Min Act: -0.0001

Data Index: 41363 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.7973. Min Act: -0.0001

Data Index: 814588 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.7645. Min Act: -0.0001

Data Index: 54324 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.7826. Min Act: -0.0001

Data Index: 571400 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.8186. Min Act: -0.0001

Data Index: 740820 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.7655. Min Act: -0.0001

Data Index: 798615 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.7883. Min Act: -0.0001

Data Index: 316657 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.7864. Min Act: -0.0001

Data Index: 870725 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.7259. Min Act: -0.0001

Data Index: 27534 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.7515. Min Act: -0.0001

Data Index: 1112715 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.6982. Min Act: -0.0001

Data Index: 537888 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.6660. Min Act: -0.0001

Data Index: 198931 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.7425. Min Act: -0.0001

Data Index: 1018084 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.6916. Min Act: -0.0001

Data Index: 766695 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.7162. Min Act: -0.0001

Data Index: 515982 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.6829. Min Act: -0.0001

Data Index: 504675 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.7076. Min Act: -0.0001

Data Index: 1247443 (C4 (Web Text))

Max Activating Token Index: 226