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

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

Neuron 1891 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.6631. Min Act: -0.0000

Data Index: 60558 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1294750 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5868. Min Act: 0.0002

Data Index: 1274970 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5307. Min Act: 0.0000

Data Index: 1119015 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5201. Min Act: -0.0000

Data Index: 988052 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5040. Min Act: -0.0000

Data Index: 215101 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5143. Min Act: 0.0001

Data Index: 634788 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5000. Min Act: -0.0000

Data Index: 827879 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5197. Min Act: 0.0001

Data Index: 271791 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5025. Min Act: -0.0000

Data Index: 160852 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5014. Min Act: 0.0000

Data Index: 871336 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.4860. Min Act: -0.0000

Data Index: 93697 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.4823. Min Act: 0.0004

Data Index: 26220 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.4994. Min Act: 0.0000

Data Index: 82164 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.4912. Min Act: 0.0002

Data Index: 532881 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.4937. Min Act: -0.0000

Data Index: 541453 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1247322 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.4749. Min Act: 0.0000

Data Index: 11766 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1254367 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.4511. Min Act: -0.0000

Data Index: 15228 (C4 (Web Text))

Max Activating Token Index: 749