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

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

Neuron 2715 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.5347. Min Act: -0.0000

Data Index: 586236 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.6315. Min Act: -0.0000

Data Index: 141094 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.5923. Min Act: -0.0000

Data Index: 1085728 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.4565. Min Act: -0.0001

Data Index: 20403 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.1850. Min Act: -0.0000

Data Index: 132685 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.2827. Min Act: -0.0000

Data Index: 1228670 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.3478. Min Act: -0.0000

Data Index: 379273 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.1556. Min Act: -0.0000

Data Index: 474638 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.0456. Min Act: -0.0000

Data Index: 574663 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.2257. Min Act: -0.0000

Data Index: 340982 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.0566. Min Act: -0.0000

Data Index: 98803 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.9440. Min Act: -0.0000

Data Index: 638138 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.7905. Min Act: -0.0000

Data Index: 213825 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.8723. Min Act: -0.0000

Data Index: 888648 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.8828. Min Act: -0.0000

Data Index: 183139 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.8139. Min Act: -0.0000

Data Index: 823271 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.8888. Min Act: -0.0000

Data Index: 96174 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.5918. Min Act: -0.0000

Data Index: 1278976 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.5631. Min Act: -0.0000

Data Index: 621204 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.6428. Min Act: -0.0000

Data Index: 952545 (C4 (Web Text))

Max Activating Token Index: 470