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

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

Neuron 2324 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: 1.0377. Min Range: -1.0377

Max Act: 0.9902. Min Act: -0.0000

Data Index: 605288 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9110. Min Act: -0.0000

Data Index: 924660 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9924. Min Act: -0.0000

Data Index: 1060918 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.8403. Min Act: -0.0000

Data Index: 634335 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 1.0377. Min Range: -1.0377

Max Act: 1.0377. Min Act: -0.0000

Data Index: 1347534 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9092. Min Act: -0.0000

Data Index: 236664 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9925. Min Act: -0.0000

Data Index: 621632 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1387719 (Python Code)

Max Activating Token Index: 857

Text #8

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9335. Min Act: -0.0000

Data Index: 1209241 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9776. Min Act: -0.0000

Data Index: 991503 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9894. Min Act: -0.0000

Data Index: 386023 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.8514. Min Act: -0.0000

Data Index: 918867 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1357452 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.8527. Min Act: -0.0000

Data Index: 454910 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.8305. Min Act: -0.0000

Data Index: 1358697 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9030. Min Act: -0.0000

Data Index: 573158 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.8108. Min Act: -0.0000

Data Index: 578639 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.8615. Min Act: -0.0000

Data Index: 357095 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.7916. Min Act: -0.0000

Data Index: 442586 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.8213. Min Act: -0.0000

Data Index: 1432729 (Python Code)

Max Activating Token Index: 425