Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1250 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.3250. Min Act: -0.0001

Data Index: 1306952 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.2797. Min Act: -0.0001

Data Index: 424652 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.3566. Min Act: -0.0001

Data Index: 1343878 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.2815. Min Act: -0.0001

Data Index: 60555 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.2661. Min Act: -0.0001

Data Index: 738367 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.2934. Min Act: -0.0001

Data Index: 287798 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.2599. Min Act: -0.0001

Data Index: 1209372 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.1637. Min Act: -0.0001

Data Index: 126674 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.2815. Min Act: -0.0001

Data Index: 536932 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.1836. Min Act: -0.0001

Data Index: 157738 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.0816. Min Act: -0.0001

Data Index: 824709 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.1067. Min Act: -0.0001

Data Index: 1205791 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.1268. Min Act: -0.0001

Data Index: 729912 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.1622. Min Act: -0.0001

Data Index: 937371 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.1473. Min Act: -0.0001

Data Index: 1152047 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.1293. Min Act: -0.0001

Data Index: 1117715 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.1211. Min Act: -0.0001

Data Index: 1206288 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.1489. Min Act: -0.0001

Data Index: 223024 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.1811. Min Act: -0.0001

Data Index: 812249 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.1111. Min Act: -0.0001

Data Index: 723477 (C4 (Web Text))

Max Activating Token Index: 597