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

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

Neuron 5895 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: 0.7153. Min Range: -0.7153

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1225231 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.6981. Min Act: -0.0000

Data Index: 76231 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.5422. Min Act: -0.0000

Data Index: 92339 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1123534 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.5191. Min Act: -0.0001

Data Index: 561682 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.5090. Min Act: -0.0000

Data Index: 134945 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.5434. Min Act: -0.0000

Data Index: 774434 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.4908. Min Act: -0.0001

Data Index: 513767 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.4855. Min Act: -0.0001

Data Index: 857889 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1069953 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1019426 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.5056. Min Act: -0.0000

Data Index: 748025 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.4824. Min Act: -0.0000

Data Index: 227976 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.4973. Min Act: -0.0001

Data Index: 14667 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.4492. Min Act: -0.0001

Data Index: 811227 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.4747. Min Act: -0.0000

Data Index: 642100 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1120541 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.4387. Min Act: -0.0000

Data Index: 600467 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1344769 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 0.7153. Min Range: -0.7153

Max Act: 0.4794. Min Act: -0.0001

Data Index: 294141 (C4 (Web Text))

Max Activating Token Index: 66