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

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

Neuron 1932 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0784. Min Act: -0.0002

Data Index: 1238227 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0759. Min Act: -0.0002

Data Index: 82136 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0685. Min Act: -0.0002

Data Index: 583891 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1294829 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0573. Min Act: -0.0002

Data Index: 787604 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0542. Min Act: -0.0002

Data Index: 473942 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0564. Min Act: -0.0003

Data Index: 151153 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1234317 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0550. Min Act: -0.0002

Data Index: 298167 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1180171 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1123099 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0512. Min Act: -0.0002

Data Index: 212091 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1283874 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0515. Min Act: -0.0003

Data Index: 1173838 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0487. Min Act: -0.0002

Data Index: 29144 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0494. Min Act: -0.0002

Data Index: 1219635 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0487. Min Act: -0.0002

Data Index: 385555 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0494. Min Act: -0.0003

Data Index: 765726 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1031174 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1172919 (C4 (Web Text))

Max Activating Token Index: 775