Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2205 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0549. Min Range: -1.0549

Max Act: 1.0549. Min Act: -0.0001

Data Index: 327272 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.5680. Min Act: -0.0001

Data Index: 1270431 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.9893. Min Act: -0.0001

Data Index: 761868 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.9672. Min Act: -0.0001

Data Index: 1229802 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8905. Min Act: -0.0001

Data Index: 965810 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.9005. Min Act: -0.0001

Data Index: 916971 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.9610. Min Act: -0.0001

Data Index: 772854 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8834. Min Act: -0.0001

Data Index: 631984 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8811. Min Act: -0.0001

Data Index: 567160 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8753. Min Act: -0.0001

Data Index: 275936 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.9295. Min Act: -0.0001

Data Index: 1347775 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8873. Min Act: -0.0001

Data Index: 557122 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8548. Min Act: -0.0001

Data Index: 299388 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.9069. Min Act: -0.0001

Data Index: 570564 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8049. Min Act: -0.0001

Data Index: 1323776 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8361. Min Act: -0.0001

Data Index: 115474 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8301. Min Act: -0.0001

Data Index: 303014 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.7603. Min Act: -0.0001

Data Index: 233035 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.7978. Min Act: -0.0001

Data Index: 1105523 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8123. Min Act: -0.0001

Data Index: 634690 (C4 (Web Text))

Max Activating Token Index: 428