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

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

Neuron 3216 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3246. Min Act: -0.0000

Data Index: 1184107 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.4511. Min Act: -0.0000

Data Index: 748934 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.4054. Min Act: -0.0000

Data Index: 954293 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.3016. Min Act: -0.0000

Data Index: 1002083 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.2891. Min Act: -0.0000

Data Index: 721026 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.2885. Min Act: -0.0000

Data Index: 1209343 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.2915. Min Act: -0.0000

Data Index: 892486 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.1744. Min Act: -0.0000

Data Index: 296618 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.2279. Min Act: -0.0000

Data Index: 474137 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.1880. Min Act: -0.0000

Data Index: 1056045 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.2295. Min Act: -0.0000

Data Index: 742850 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.1680. Min Act: -0.0000

Data Index: 1249475 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.2464. Min Act: -0.0000

Data Index: 103554 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.2096. Min Act: -0.0000

Data Index: 502145 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.2010. Min Act: -0.0000

Data Index: 1256596 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.0932. Min Act: -0.0000

Data Index: 809195 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.1338. Min Act: -0.0000

Data Index: 714926 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.1372. Min Act: -0.0000

Data Index: 1278836 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.1080. Min Act: -0.0000

Data Index: 687031 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 1.4511. Min Range: -1.4511

Max Act: 1.0568. Min Act: -0.0000

Data Index: 299317 (C4 (Web Text))

Max Activating Token Index: 612