Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1385 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.8558. Min Act: -0.0000

Data Index: 387498 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.9593. Min Act: -0.0000

Data Index: 1223891 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.8344. Min Act: -0.0000

Data Index: 843987 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.8898. Min Act: -0.0001

Data Index: 420953 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.6702. Min Act: -0.0000

Data Index: 1294679 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.8110. Min Act: -0.0001

Data Index: 1144550 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.7863. Min Act: -0.0001

Data Index: 470439 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.6852. Min Act: -0.0001

Data Index: 496548 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.5831. Min Act: -0.0001

Data Index: 342228 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.6672. Min Act: -0.0001

Data Index: 845095 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.5699. Min Act: -0.0000

Data Index: 1355484 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.7377. Min Act: -0.0001

Data Index: 463964 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.6538. Min Act: -0.0000

Data Index: 581380 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.6334. Min Act: -0.0000

Data Index: 930288 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.7096. Min Act: -0.0000

Data Index: 1005169 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.6038. Min Act: -0.0001

Data Index: 678540 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.5998. Min Act: -0.0000

Data Index: 137472 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.5854. Min Act: -0.0000

Data Index: 746540 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.4764. Min Act: -0.0001

Data Index: 1126725 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 1.9593. Min Range: -1.9593

Max Act: 1.4707. Min Act: -0.0001

Data Index: 197076 (C4 (Web Text))

Max Activating Token Index: 926