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

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

Neuron 5854 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0132. Min Range: -1.0132

Max Act: 1.0132. Min Act: -0.0000

Data Index: 21251 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.9284. Min Act: -0.0000

Data Index: 688404 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.8009. Min Act: -0.0000

Data Index: 885193 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.8629. Min Act: -0.0000

Data Index: 984375 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7954. Min Act: -0.0000

Data Index: 569703 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.8447. Min Act: -0.0000

Data Index: 152874 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7581. Min Act: -0.0000

Data Index: 242144 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.8371. Min Act: -0.0000

Data Index: 467657 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7187. Min Act: -0.0000

Data Index: 528285 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7909. Min Act: -0.0000

Data Index: 190250 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7617. Min Act: -0.0000

Data Index: 1082841 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7349. Min Act: -0.0000

Data Index: 423077 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7529. Min Act: -0.0000

Data Index: 486282 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7765. Min Act: -0.0000

Data Index: 1117977 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7742. Min Act: -0.0000

Data Index: 345664 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7948. Min Act: -0.0000

Data Index: 795761 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7672. Min Act: -0.0000

Data Index: 898306 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7168. Min Act: -0.0000

Data Index: 633868 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7773. Min Act: -0.0000

Data Index: 884247 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7736. Min Act: -0.0000

Data Index: 499150 (C4 (Web Text))

Max Activating Token Index: 888