Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 15 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1041063 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4732. Min Act: -0.0000

Data Index: 637018 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4700. Min Act: -0.0000

Data Index: 534991 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4475. Min Act: -0.0000

Data Index: 152264 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4201. Min Act: -0.0000

Data Index: 806200 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4149. Min Act: -0.0000

Data Index: 296636 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4248. Min Act: -0.0000

Data Index: 541275 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4023. Min Act: -0.0001

Data Index: 645427 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.3850. Min Act: -0.0000

Data Index: 585439 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.3631. Min Act: -0.0000

Data Index: 145123 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.3723. Min Act: -0.0000

Data Index: 3262 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.3579. Min Act: -0.0000

Data Index: 984581 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.3614. Min Act: -0.0000

Data Index: 772039 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.3666. Min Act: -0.0000

Data Index: 808015 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.3767. Min Act: -0.0000

Data Index: 842030 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.3625. Min Act: -0.0000

Data Index: 374645 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.3477. Min Act: -0.0000

Data Index: 311444 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1184356 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.3327. Min Act: -0.0000

Data Index: 544546 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.3159. Min Act: -0.0000

Data Index: 89536 (C4 (Web Text))

Max Activating Token Index: 358