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

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

Neuron 3063 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: 4.7460. Min Range: -4.7460

Max Act: 4.7460. Min Act: -0.0000

Data Index: 724855 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 4.7460. Min Range: -4.7460

Max Act: 4.7064. Min Act: -0.0000

Data Index: 636722 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 4.7460. Min Range: -4.7460

Max Act: 3.6812. Min Act: -0.0000

Data Index: 639996 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 4.7460. Min Range: -4.7460

Max Act: 3.5524. Min Act: -0.0000

Data Index: 1108998 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 4.7460. Min Range: -4.7460

Max Act: 3.5035. Min Act: -0.0000

Data Index: 349145 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 4.7460. Min Range: -4.7460

Max Act: 3.1541. Min Act: -0.0000

Data Index: 520119 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 4.7460. Min Range: -4.7460

Max Act: 3.5558. Min Act: -0.0000

Data Index: 199505 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 4.7460. Min Range: -4.7460

Max Act: 3.4950. Min Act: -0.0000

Data Index: 950753 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 4.7460. Min Range: -4.7460

Max Act: 3.0728. Min Act: -0.0000

Data Index: 519394 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 4.7460. Min Range: -4.7460

Max Act: 2.2805. Min Act: -0.0000

Data Index: 1062542 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 4.7460. Min Range: -4.7460

Max Act: 2.5559. Min Act: -0.0000

Data Index: 668641 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 4.7460. Min Range: -4.7460

Max Act: 2.1589. Min Act: -0.0000

Data Index: 424223 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 4.7460. Min Range: -4.7460

Max Act: 2.3115. Min Act: -0.0000

Data Index: 154229 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 4.7460. Min Range: -4.7460

Max Act: 2.4398. Min Act: -0.0000

Data Index: 1333514 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 4.7460. Min Range: -4.7460

Max Act: 2.3933. Min Act: -0.0000

Data Index: 108635 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 4.7460. Min Range: -4.7460

Max Act: 2.4742. Min Act: -0.0000

Data Index: 1155807 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 4.7460. Min Range: -4.7460

Max Act: 2.4280. Min Act: -0.0000

Data Index: 446577 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 4.7460. Min Range: -4.7460

Max Act: 2.3944. Min Act: -0.0000

Data Index: 408155 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 4.7460. Min Range: -4.7460

Max Act: 2.1381. Min Act: -0.0000

Data Index: 641321 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 4.7460. Min Range: -4.7460

Max Act: 1.9024. Min Act: -0.0000

Data Index: 263936 (C4 (Web Text))

Max Activating Token Index: 677