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

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

Neuron 1073 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: 0.6302. Min Range: -0.6302

Max Act: 0.6302. Min Act: -0.0000

Data Index: 276094 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.6048. Min Act: -0.0000

Data Index: 595303 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1156620 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.5385. Min Act: -0.0000

Data Index: 430554 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1112579 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.5124. Min Act: -0.0000

Data Index: 1113107 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.5293. Min Act: -0.0000

Data Index: 318923 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.4793. Min Act: -0.0000

Data Index: 201157 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1017539 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.4769. Min Act: -0.0000

Data Index: 373209 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.5005. Min Act: -0.0000

Data Index: 940504 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1319677 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.4584. Min Act: -0.0000

Data Index: 372740 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.4833. Min Act: -0.0000

Data Index: 934601 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.4651. Min Act: -0.0000

Data Index: 221959 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.4718. Min Act: -0.0000

Data Index: 686577 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.4848. Min Act: -0.0000

Data Index: 235706 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.4366. Min Act: -0.0000

Data Index: 539586 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1134332 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.6302. Min Range: -0.6302

Max Act: 0.4417. Min Act: -0.0000

Data Index: 675431 (C4 (Web Text))

Max Activating Token Index: 489