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

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

Neuron 1640 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.9731. Min Act: -0.0000

Data Index: 113886 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.9520. Min Act: -0.0000

Data Index: 1159609 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8846. Min Act: -0.0000

Data Index: 753839 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8812. Min Act: -0.0000

Data Index: 917485 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8238. Min Act: -0.0000

Data Index: 1122521 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1298092 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1064143 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8413. Min Act: -0.0000

Data Index: 1248557 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8672. Min Act: -0.0000

Data Index: 821123 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8270. Min Act: -0.0000

Data Index: 824747 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8183. Min Act: -0.0000

Data Index: 515498 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7678. Min Act: -0.0000

Data Index: 627932 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8621. Min Act: -0.0000

Data Index: 960027 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7570. Min Act: -0.0000

Data Index: 640656 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1079630 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7971. Min Act: -0.0000

Data Index: 926581 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7857. Min Act: -0.0000

Data Index: 1190464 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7364. Min Act: -0.0000

Data Index: 288986 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7982. Min Act: -0.0000

Data Index: 914063 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7647. Min Act: -0.0000

Data Index: 838953 (C4 (Web Text))

Max Activating Token Index: 180