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

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

Neuron 5375 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: 3.0222. Min Range: -3.0222

Max Act: 3.0222. Min Act: -0.0000

Data Index: 849803 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 3.0222. Min Range: -3.0222

Max Act: 2.8373. Min Act: -0.0000

Data Index: 142525 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 3.0222. Min Range: -3.0222

Max Act: 2.8871. Min Act: -0.0000

Data Index: 1301270 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 3.0222. Min Range: -3.0222

Max Act: 2.7312. Min Act: -0.0000

Data Index: 282332 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 3.0222. Min Range: -3.0222

Max Act: 2.3113. Min Act: -0.0000

Data Index: 1193321 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 3.0222. Min Range: -3.0222

Max Act: 2.3973. Min Act: -0.0000

Data Index: 1251444 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 3.0222. Min Range: -3.0222

Max Act: 2.3959. Min Act: -0.0000

Data Index: 570444 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 3.0222. Min Range: -3.0222

Max Act: 2.1921. Min Act: -0.0001

Data Index: 333862 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 3.0222. Min Range: -3.0222

Max Act: 2.1767. Min Act: -0.0000

Data Index: 877524 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 3.0222. Min Range: -3.0222

Max Act: 2.4116. Min Act: -0.0001

Data Index: 627900 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 3.0222. Min Range: -3.0222

Max Act: 2.2767. Min Act: -0.0000

Data Index: 552858 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 3.0222. Min Range: -3.0222

Max Act: 2.2744. Min Act: -0.0000

Data Index: 78009 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 3.0222. Min Range: -3.0222

Max Act: 2.0815. Min Act: -0.0000

Data Index: 721401 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 3.0222. Min Range: -3.0222

Max Act: 2.1206. Min Act: -0.0000

Data Index: 179331 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 3.0222. Min Range: -3.0222

Max Act: 1.9963. Min Act: -0.0000

Data Index: 873467 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 3.0222. Min Range: -3.0222

Max Act: 2.1119. Min Act: -0.0000

Data Index: 998981 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 3.0222. Min Range: -3.0222

Max Act: 1.9250. Min Act: -0.0001

Data Index: 1100530 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 3.0222. Min Range: -3.0222

Max Act: 1.9852. Min Act: -0.0000

Data Index: 1299962 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 3.0222. Min Range: -3.0222

Max Act: 2.2052. Min Act: -0.0001

Data Index: 161843 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 3.0222. Min Range: -3.0222

Max Act: 1.8619. Min Act: -0.0000

Data Index: 321505 (C4 (Web Text))

Max Activating Token Index: 613