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

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

Neuron 581 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: 0.8180. Min Range: -0.8180

Max Act: 0.8180. Min Act: -0.0000

Data Index: 602883 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7577. Min Act: -0.0000

Data Index: 316351 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7657. Min Act: -0.0000

Data Index: 664836 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1453325 (Python Code)

Max Activating Token Index: 239

Text #4

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1422574 (Python Code)

Max Activating Token Index: 744

Text #5

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7008. Min Act: -0.0000

Data Index: 1185741 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1397187 (Python Code)

Max Activating Token Index: 104

Text #7

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1193282 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.5963. Min Act: -0.0000

Data Index: 722308 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1279814 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.5486. Min Act: -0.0000

Data Index: 674407 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6098. Min Act: -0.0000

Data Index: 1415094 (Python Code)

Max Activating Token Index: 901

Text #12

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1002348 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.5433. Min Act: -0.0000

Data Index: 885463 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6069. Min Act: -0.0000

Data Index: 403362 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1370682 (Python Code)

Max Activating Token Index: 816

Text #16

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.5205. Min Act: -0.0000

Data Index: 831202 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.5802. Min Act: -0.0000

Data Index: 653318 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1284417 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.5086. Min Act: -0.0000

Data Index: 550230 (C4 (Web Text))

Max Activating Token Index: 593