Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4892 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0786. Min Range: -1.0786

Max Act: 1.0786. Min Act: -0.0000

Data Index: 199502 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 1.0786. Min Range: -1.0786

Max Act: 1.0275. Min Act: -0.0000

Data Index: 1307576 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 1.0786. Min Range: -1.0786

Max Act: 0.8884. Min Act: -0.0000

Data Index: 558734 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 1.0786. Min Range: -1.0786

Max Act: 0.8783. Min Act: -0.0000

Data Index: 208199 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.0786. Min Range: -1.0786

Max Act: 0.8353. Min Act: -0.0000

Data Index: 1165429 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 1.0786. Min Range: -1.0786

Max Act: 0.8441. Min Act: -0.0000

Data Index: 367787 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 1.0786. Min Range: -1.0786

Max Act: 0.8014. Min Act: -0.0000

Data Index: 42325 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 1.0786. Min Range: -1.0786

Max Act: 0.8226. Min Act: -0.0000

Data Index: 1243148 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 1.0786. Min Range: -1.0786

Max Act: 0.7862. Min Act: -0.0000

Data Index: 839206 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 1.0786. Min Range: -1.0786

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1267542 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 1.0786. Min Range: -1.0786

Max Act: 0.7694. Min Act: -0.0000

Data Index: 1309822 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 1.0786. Min Range: -1.0786

Max Act: 0.7407. Min Act: -0.0000

Data Index: 1006913 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 1.0786. Min Range: -1.0786

Max Act: 0.7647. Min Act: -0.0000

Data Index: 957965 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 1.0786. Min Range: -1.0786

Max Act: 0.7403. Min Act: -0.0000

Data Index: 1256685 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 1.0786. Min Range: -1.0786

Max Act: 0.7157. Min Act: -0.0000

Data Index: 1359554 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 1.0786. Min Range: -1.0786

Max Act: 0.7722. Min Act: -0.0000

Data Index: 1054870 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 1.0786. Min Range: -1.0786

Max Act: 0.7057. Min Act: -0.0000

Data Index: 8857 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 1.0786. Min Range: -1.0786

Max Act: 0.6613. Min Act: -0.0000

Data Index: 369794 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 1.0786. Min Range: -1.0786

Max Act: 0.7022. Min Act: -0.0000

Data Index: 102418 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 1.0786. Min Range: -1.0786

Max Act: 0.6114. Min Act: -0.0000

Data Index: 1251511 (C4 (Web Text))

Max Activating Token Index: 301