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

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

Neuron 910 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0899. Min Range: -2.0899

Max Act: 2.0465. Min Act: -0.0001

Data Index: 779564 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 2.0899. Min Range: -2.0899

Max Act: 2.0269. Min Act: -0.0001

Data Index: 82231 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 2.0899. Min Range: -2.0899

Max Act: 2.0899. Min Act: -0.0000

Data Index: 105156 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.9245. Min Act: -0.0001

Data Index: 942049 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.6307. Min Act: -0.0001

Data Index: 696721 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.4360. Min Act: -0.0000

Data Index: 704586 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.4468. Min Act: -0.0000

Data Index: 566331 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.5791. Min Act: -0.0000

Data Index: 260719 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.3758. Min Act: -0.0000

Data Index: 1061045 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.4408. Min Act: -0.0001

Data Index: 516879 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.3599. Min Act: -0.0000

Data Index: 427883 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.2549. Min Act: -0.0000

Data Index: 1191953 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.1158. Min Act: -0.0001

Data Index: 588707 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.1215. Min Act: -0.0001

Data Index: 1206923 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.1386. Min Act: -0.0000

Data Index: 1180141 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.1112. Min Act: -0.0000

Data Index: 1210510 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.0347. Min Act: -0.0000

Data Index: 143535 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.1396. Min Act: -0.0001

Data Index: 1328717 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.0719. Min Act: -0.0000

Data Index: 972554 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.1061. Min Act: -0.0000

Data Index: 190887 (C4 (Web Text))

Max Activating Token Index: 794