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

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

Neuron 3104 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1061. Min Range: -1.1061

Max Act: 1.1061. Min Act: -0.0000

Data Index: 196346 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 1.1061. Min Range: -1.1061

Max Act: 1.0996. Min Act: -0.0000

Data Index: 1155258 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 1.1061. Min Range: -1.1061

Max Act: 1.0148. Min Act: -0.0000

Data Index: 838263 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9993. Min Act: -0.0000

Data Index: 286836 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9599. Min Act: -0.0000

Data Index: 1142624 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 1.1061. Min Range: -1.1061

Max Act: 1.0172. Min Act: -0.0000

Data Index: 599834 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9451. Min Act: -0.0000

Data Index: 235690 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9115. Min Act: -0.0000

Data Index: 425384 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9950. Min Act: -0.0000

Data Index: 920403 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9564. Min Act: -0.0000

Data Index: 807376 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1025562 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9138. Min Act: -0.0000

Data Index: 546704 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.8109. Min Act: -0.0000

Data Index: 806865 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.8822. Min Act: -0.0001

Data Index: 507997 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9225. Min Act: -0.0000

Data Index: 548101 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9157. Min Act: -0.0000

Data Index: 620881 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.8886. Min Act: -0.0000

Data Index: 571210 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1348180 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.8648. Min Act: -0.0000

Data Index: 11504 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.8614. Min Act: -0.0001

Data Index: 988930 (C4 (Web Text))

Max Activating Token Index: 56