Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1307 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9079. Min Range: -1.9079

Max Act: 1.9079. Min Act: -0.0000

Data Index: 1373079 (Python Code)

Max Activating Token Index: 539

Text #1

Max Range: 1.9079. Min Range: -1.9079

Max Act: 1.1982. Min Act: -0.0000

Data Index: 1134176 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 1.9079. Min Range: -1.9079

Max Act: 1.0487. Min Act: -0.0000

Data Index: 448318 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 1.9079. Min Range: -1.9079

Max Act: 0.9899. Min Act: -0.0000

Data Index: 677942 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 1.9079. Min Range: -1.9079

Max Act: 1.1059. Min Act: -0.0000

Data Index: 210290 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 1.9079. Min Range: -1.9079

Max Act: 1.1584. Min Act: -0.0000

Data Index: 1141004 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 1.9079. Min Range: -1.9079

Max Act: 1.0413. Min Act: -0.0000

Data Index: 1041678 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.9079. Min Range: -1.9079

Max Act: 1.0565. Min Act: -0.0000

Data Index: 1088532 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 1.9079. Min Range: -1.9079

Max Act: 1.0480. Min Act: -0.0000

Data Index: 344595 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 1.9079. Min Range: -1.9079

Max Act: 0.9488. Min Act: -0.0000

Data Index: 641468 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 1.9079. Min Range: -1.9079

Max Act: 1.0233. Min Act: -0.0000

Data Index: 455911 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 1.9079. Min Range: -1.9079

Max Act: 0.9689. Min Act: -0.0000

Data Index: 27589 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 1.9079. Min Range: -1.9079

Max Act: 0.9542. Min Act: -0.0000

Data Index: 776442 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 1.9079. Min Range: -1.9079

Max Act: 0.8840. Min Act: -0.0000

Data Index: 176619 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 1.9079. Min Range: -1.9079

Max Act: 0.8805. Min Act: 0.0000

Data Index: 396684 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 1.9079. Min Range: -1.9079

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1073172 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 1.9079. Min Range: -1.9079

Max Act: 0.9793. Min Act: -0.0000

Data Index: 1236477 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 1.9079. Min Range: -1.9079

Max Act: 0.8864. Min Act: -0.0000

Data Index: 150221 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 1.9079. Min Range: -1.9079

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1312431 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 1.9079. Min Range: -1.9079

Max Act: 0.8175. Min Act: -0.0000

Data Index: 917122 (C4 (Web Text))

Max Activating Token Index: 729