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

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

Neuron 83 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: 0.1341. Min Range: -0.1341

Max Act: 0.1233. Min Act: -0.0000

Data Index: 576012 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1341. Min Act: -0.0000

Data Index: 776877 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1111132 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1064. Min Act: -0.0001

Data Index: 65450 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1108. Min Act: -0.0001

Data Index: 827487 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1138. Min Act: -0.0000

Data Index: 299223 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1161. Min Act: -0.0001

Data Index: 530021 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1070. Min Act: -0.0001

Data Index: 798180 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1099. Min Act: -0.0001

Data Index: 715929 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1026. Min Act: -0.0001

Data Index: 893544 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1060. Min Act: -0.0000

Data Index: 785018 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1189301 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0985. Min Act: -0.0001

Data Index: 24474 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1049. Min Act: -0.0001

Data Index: 960895 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0968. Min Act: -0.0001

Data Index: 128524 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1009. Min Act: -0.0000

Data Index: 363075 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1311963 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0974. Min Act: -0.0001

Data Index: 1173881 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1027. Min Act: -0.0000

Data Index: 477316 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1030. Min Act: -0.0001

Data Index: 165373 (C4 (Web Text))

Max Activating Token Index: 636