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

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

Neuron 3200 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.6177. Min Act: -0.0000

Data Index: 1235817 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.1978. Min Act: -0.0000

Data Index: 104430 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 3.6177. Min Range: -3.6177

Max Act: 1.7911. Min Act: -0.0000

Data Index: 120358 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 3.6177. Min Range: -3.6177

Max Act: 1.3629. Min Act: -0.0000

Data Index: 460219 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 3.6177. Min Range: -3.6177

Max Act: 1.2252. Min Act: -0.0000

Data Index: 721803 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 3.6177. Min Range: -3.6177

Max Act: 1.2824. Min Act: -0.0000

Data Index: 787915 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 3.6177. Min Range: -3.6177

Max Act: 1.3121. Min Act: -0.0000

Data Index: 84536 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 3.6177. Min Range: -3.6177

Max Act: 1.2445. Min Act: -0.0000

Data Index: 702840 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 3.6177. Min Range: -3.6177

Max Act: 1.2658. Min Act: -0.0000

Data Index: 433478 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 3.6177. Min Range: -3.6177

Max Act: 1.1864. Min Act: -0.0000

Data Index: 888980 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 3.6177. Min Range: -3.6177

Max Act: 1.1642. Min Act: -0.0000

Data Index: 158640 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 3.6177. Min Range: -3.6177

Max Act: 1.1783. Min Act: -0.0000

Data Index: 1020836 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 3.6177. Min Range: -3.6177

Max Act: 1.1525. Min Act: -0.0000

Data Index: 13115 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 3.6177. Min Range: -3.6177

Max Act: 1.1296. Min Act: -0.0000

Data Index: 1344364 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 3.6177. Min Range: -3.6177

Max Act: 1.1155. Min Act: -0.0000

Data Index: 1069740 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 3.6177. Min Range: -3.6177

Max Act: 1.0519. Min Act: -0.0000

Data Index: 590981 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 3.6177. Min Range: -3.6177

Max Act: 1.0949. Min Act: -0.0000

Data Index: 344909 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 3.6177. Min Range: -3.6177

Max Act: 1.1010. Min Act: -0.0000

Data Index: 1175796 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 3.6177. Min Range: -3.6177

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1324406 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 3.6177. Min Range: -3.6177

Max Act: 1.1191. Min Act: -0.0000

Data Index: 178351 (C4 (Web Text))

Max Activating Token Index: 835