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

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

Neuron 682 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.4438. Min Act: -0.0000

Data Index: 1320686 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.4148. Min Act: -0.0000

Data Index: 286823 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.0458. Min Act: -0.0000

Data Index: 1292123 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 1.4438. Min Range: -1.4438

Max Act: 0.9536. Min Act: -0.0000

Data Index: 1435059 (Python Code)

Max Activating Token Index: 780

Text #4

Max Range: 1.4438. Min Range: -1.4438

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1552751 (Python Code)

Max Activating Token Index: 905

Text #5

Max Range: 1.4438. Min Range: -1.4438

Max Act: 0.8916. Min Act: -0.0000

Data Index: 917574 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 1.4438. Min Range: -1.4438

Max Act: 0.9405. Min Act: -0.0000

Data Index: 450391 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 1.4438. Min Range: -1.4438

Max Act: 0.9609. Min Act: -0.0000

Data Index: 790627 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 1.4438. Min Range: -1.4438

Max Act: 0.9304. Min Act: -0.0000

Data Index: 945867 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 1.4438. Min Range: -1.4438

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1565174 (Python Code)

Max Activating Token Index: 272

Text #10

Max Range: 1.4438. Min Range: -1.4438

Max Act: 0.9569. Min Act: -0.0000

Data Index: 1309370 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 1.4438. Min Range: -1.4438

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1105383 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 1.4438. Min Range: -1.4438

Max Act: 0.8980. Min Act: -0.0000

Data Index: 1593280 (Python Code)

Max Activating Token Index: 92

Text #13

Max Range: 1.4438. Min Range: -1.4438

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1137354 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 1.4438. Min Range: -1.4438

Max Act: 0.8583. Min Act: -0.0000

Data Index: 1385149 (Python Code)

Max Activating Token Index: 1000

Text #15

Max Range: 1.4438. Min Range: -1.4438

Max Act: 0.9453. Min Act: -0.0000

Data Index: 1406103 (Python Code)

Max Activating Token Index: 997

Text #16

Max Range: 1.4438. Min Range: -1.4438

Max Act: 0.9151. Min Act: -0.0000

Data Index: 918747 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 1.4438. Min Range: -1.4438

Max Act: 0.8864. Min Act: -0.0000

Data Index: 1520978 (Python Code)

Max Activating Token Index: 588

Text #18

Max Range: 1.4438. Min Range: -1.4438

Max Act: 0.8653. Min Act: -0.0000

Data Index: 949293 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 1.4438. Min Range: -1.4438

Max Act: 0.8218. Min Act: -0.0000

Data Index: 785930 (C4 (Web Text))

Max Activating Token Index: 714