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

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

Neuron 1419 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.6363. Min Act: -0.0000

Data Index: 339388 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.4417. Min Act: -0.0000

Data Index: 1062875 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.6044. Min Act: -0.0000

Data Index: 331225 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.3828. Min Act: -0.0000

Data Index: 30152 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.3502. Min Act: -0.0000

Data Index: 596502 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.3635. Min Act: -0.0000

Data Index: 1135776 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.1777. Min Act: -0.0000

Data Index: 479309 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.0377. Min Act: -0.0000

Data Index: 366883 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.0514. Min Act: -0.0000

Data Index: 1135665 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 1.6363. Min Range: -1.6363

Max Act: 0.9512. Min Act: -0.0000

Data Index: 1249123 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.0428. Min Act: -0.0000

Data Index: 410212 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 1.6363. Min Range: -1.6363

Max Act: 0.9921. Min Act: -0.0000

Data Index: 933050 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 1.6363. Min Range: -1.6363

Max Act: 0.9532. Min Act: -0.0000

Data Index: 517348 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 1.6363. Min Range: -1.6363

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1632897 (Python Code)

Max Activating Token Index: 494

Text #14

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.0023. Min Act: -0.0000

Data Index: 996855 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 1.6363. Min Range: -1.6363

Max Act: 0.8873. Min Act: -0.0000

Data Index: 792490 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 1.6363. Min Range: -1.6363

Max Act: 0.8709. Min Act: -0.0000

Data Index: 61294 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 1.6363. Min Range: -1.6363

Max Act: 0.9166. Min Act: -0.0000

Data Index: 651922 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 1.6363. Min Range: -1.6363

Max Act: 0.9161. Min Act: -0.0000

Data Index: 538887 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 1.6363. Min Range: -1.6363

Max Act: 0.9689. Min Act: -0.0000

Data Index: 97291 (C4 (Web Text))

Max Activating Token Index: 382