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

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

Neuron 4688 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: 0.8174. Min Range: -0.8174

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1276425 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7480. Min Act: -0.0000

Data Index: 1343086 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.8174. Min Act: -0.0000

Data Index: 118688 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7195. Min Act: -0.0000

Data Index: 359640 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7417. Min Act: -0.0000

Data Index: 377290 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6782. Min Act: -0.0000

Data Index: 642621 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6643. Min Act: -0.0000

Data Index: 1049062 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6786. Min Act: -0.0000

Data Index: 916993 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1284522 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5602. Min Act: -0.0000

Data Index: 328005 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5681. Min Act: -0.0000

Data Index: 774298 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5385. Min Act: -0.0000

Data Index: 642817 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1270556 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.4817. Min Act: -0.0000

Data Index: 115899 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.4864. Min Act: -0.0000

Data Index: 52096 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.4770. Min Act: -0.0000

Data Index: 442244 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.4252. Min Act: -0.0000

Data Index: 968061 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.4637. Min Act: -0.0000

Data Index: 431067 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.4465. Min Act: -0.0000

Data Index: 486886 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.4475. Min Act: -0.0000

Data Index: 398214 (C4 (Web Text))

Max Activating Token Index: 982