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

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

Neuron 2767 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.8672. Min Act: -0.0000

Data Index: 86701 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 6.8672. Min Range: -6.8672

Max Act: 5.5551. Min Act: -0.0000

Data Index: 112998 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 6.8672. Min Range: -6.8672

Max Act: 5.5954. Min Act: -0.0000

Data Index: 241927 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 6.8672. Min Range: -6.8672

Max Act: 5.5224. Min Act: -0.0000

Data Index: 1191971 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 6.8672. Min Range: -6.8672

Max Act: 5.5709. Min Act: -0.0000

Data Index: 367178 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 6.8672. Min Range: -6.8672

Max Act: 5.3090. Min Act: -0.0000

Data Index: 884711 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 6.8672. Min Range: -6.8672

Max Act: 5.1046. Min Act: -0.0000

Data Index: 777554 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 6.8672. Min Range: -6.8672

Max Act: 5.2128. Min Act: -0.0000

Data Index: 929721 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 6.8672. Min Range: -6.8672

Max Act: 4.8891. Min Act: -0.0000

Data Index: 623683 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 6.8672. Min Range: -6.8672

Max Act: 4.9009. Min Act: -0.0000

Data Index: 834856 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 6.8672. Min Range: -6.8672

Max Act: 4.8100. Min Act: -0.0000

Data Index: 360350 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 6.8672. Min Range: -6.8672

Max Act: 4.5773. Min Act: -0.0000

Data Index: 825013 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 6.8672. Min Range: -6.8672

Max Act: 4.5782. Min Act: -0.0000

Data Index: 827325 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 6.8672. Min Range: -6.8672

Max Act: 4.7770. Min Act: -0.0000

Data Index: 321708 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 6.8672. Min Range: -6.8672

Max Act: 4.6167. Min Act: -0.0000

Data Index: 36782 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 6.8672. Min Range: -6.8672

Max Act: 4.5612. Min Act: -0.0000

Data Index: 181394 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 6.8672. Min Range: -6.8672

Max Act: 4.4265. Min Act: -0.0000

Data Index: 723347 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 6.8672. Min Range: -6.8672

Max Act: 4.6126. Min Act: -0.0000

Data Index: 813255 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 6.8672. Min Range: -6.8672

Max Act: 4.2426. Min Act: -0.0000

Data Index: 873990 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 6.8672. Min Range: -6.8672

Max Act: 4.4358. Min Act: -0.0000

Data Index: 817223 (C4 (Web Text))

Max Activating Token Index: 940