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

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

Neuron 4140 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.7207. Min Act: -0.0000

Data Index: 143872 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.6255. Min Act: -0.0000

Data Index: 538178 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.5918. Min Act: -0.0000

Data Index: 1038788 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.5382. Min Act: -0.0000

Data Index: 517291 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.4951. Min Act: -0.0000

Data Index: 54515 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1007452 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1066670 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.4984. Min Act: -0.0000

Data Index: 1352507 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.5184. Min Act: -0.0000

Data Index: 287689 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.4715. Min Act: -0.0000

Data Index: 24816 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.5022. Min Act: -0.0000

Data Index: 601293 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.4299. Min Act: -0.0000

Data Index: 625410 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.4598. Min Act: -0.0000

Data Index: 664698 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.4721. Min Act: -0.0000

Data Index: 727004 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.4361. Min Act: -0.0000

Data Index: 393911 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.4332. Min Act: -0.0000

Data Index: 872107 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.4457. Min Act: -0.0000

Data Index: 62717 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.4544. Min Act: -0.0000

Data Index: 482271 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.4345. Min Act: -0.0000

Data Index: 714623 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.7207. Min Range: -0.7207

Max Act: 0.4092. Min Act: -0.0000

Data Index: 877060 (C4 (Web Text))

Max Activating Token Index: 267