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

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

Neuron 2861 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: 2.1870. Min Range: -2.1870

Max Act: 2.1870. Min Act: -0.0000

Data Index: 1087900 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 2.1870. Min Range: -2.1870

Max Act: 2.0106. Min Act: -0.0000

Data Index: 1233005 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 2.1870. Min Range: -2.1870

Max Act: 1.8787. Min Act: -0.0001

Data Index: 562311 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 2.1870. Min Range: -2.1870

Max Act: 1.7821. Min Act: -0.0001

Data Index: 965323 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 2.1870. Min Range: -2.1870

Max Act: 1.8035. Min Act: -0.0001

Data Index: 1238264 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 2.1870. Min Range: -2.1870

Max Act: 1.7444. Min Act: -0.0001

Data Index: 1139532 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 2.1870. Min Range: -2.1870

Max Act: 1.7804. Min Act: -0.0000

Data Index: 1358723 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 2.1870. Min Range: -2.1870

Max Act: 1.9054. Min Act: -0.0000

Data Index: 217192 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 2.1870. Min Range: -2.1870

Max Act: 1.7386. Min Act: -0.0000

Data Index: 649902 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 2.1870. Min Range: -2.1870

Max Act: 1.7210. Min Act: -0.0000

Data Index: 217446 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 2.1870. Min Range: -2.1870

Max Act: 1.5672. Min Act: -0.0001

Data Index: 247794 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 2.1870. Min Range: -2.1870

Max Act: 1.7979. Min Act: -0.0001

Data Index: 410324 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 2.1870. Min Range: -2.1870

Max Act: 1.7181. Min Act: -0.0000

Data Index: 1219487 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 2.1870. Min Range: -2.1870

Max Act: 1.6732. Min Act: -0.0000

Data Index: 574521 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 2.1870. Min Range: -2.1870

Max Act: 1.4167. Min Act: -0.0001

Data Index: 1095364 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 2.1870. Min Range: -2.1870

Max Act: 1.4924. Min Act: -0.0000

Data Index: 875463 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 2.1870. Min Range: -2.1870

Max Act: 1.5016. Min Act: -0.0000

Data Index: 1336591 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 2.1870. Min Range: -2.1870

Max Act: 1.4588. Min Act: -0.0000

Data Index: 224576 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 2.1870. Min Range: -2.1870

Max Act: 1.4143. Min Act: -0.0000

Data Index: 1242700 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 2.1870. Min Range: -2.1870

Max Act: 1.3918. Min Act: -0.0000

Data Index: 917708 (C4 (Web Text))

Max Activating Token Index: 20