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

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

Neuron 2686 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9287. Min Range: -4.9287

Max Act: 4.9287. Min Act: -0.0000

Data Index: 655486 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 4.9287. Min Range: -4.9287

Max Act: 4.6072. Min Act: -0.0000

Data Index: 465303 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 4.9287. Min Range: -4.9287

Max Act: 4.3456. Min Act: -0.0000

Data Index: 589395 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 4.9287. Min Range: -4.9287

Max Act: 3.9956. Min Act: -0.0000

Data Index: 406233 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 4.9287. Min Range: -4.9287

Max Act: 3.5305. Min Act: -0.0000

Data Index: 458738 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 4.9287. Min Range: -4.9287

Max Act: 3.5582. Min Act: -0.0000

Data Index: 128141 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 4.9287. Min Range: -4.9287

Max Act: 3.2300. Min Act: -0.0000

Data Index: 1030434 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 4.9287. Min Range: -4.9287

Max Act: 3.0092. Min Act: -0.0000

Data Index: 878174 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 4.9287. Min Range: -4.9287

Max Act: 3.1310. Min Act: -0.0000

Data Index: 907145 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 4.9287. Min Range: -4.9287

Max Act: 2.9065. Min Act: -0.0000

Data Index: 1347968 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 4.9287. Min Range: -4.9287

Max Act: 2.9954. Min Act: -0.0000

Data Index: 320161 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 4.9287. Min Range: -4.9287

Max Act: 2.9720. Min Act: -0.0000

Data Index: 198733 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 4.9287. Min Range: -4.9287

Max Act: 2.7380. Min Act: -0.0000

Data Index: 901922 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 4.9287. Min Range: -4.9287

Max Act: 2.8310. Min Act: -0.0000

Data Index: 932697 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 4.9287. Min Range: -4.9287

Max Act: 2.6362. Min Act: -0.0000

Data Index: 487063 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 4.9287. Min Range: -4.9287

Max Act: 2.4795. Min Act: -0.0000

Data Index: 293472 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 4.9287. Min Range: -4.9287

Max Act: 2.5941. Min Act: -0.0000

Data Index: 637160 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 4.9287. Min Range: -4.9287

Max Act: 2.4757. Min Act: -0.0000

Data Index: 218123 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 4.9287. Min Range: -4.9287

Max Act: 2.5958. Min Act: -0.0000

Data Index: 571458 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 4.9287. Min Range: -4.9287

Max Act: 2.6074. Min Act: -0.0000

Data Index: 495865 (C4 (Web Text))

Max Activating Token Index: 47