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

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

Neuron 1558 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: 1.2397. Min Range: -1.2397

Max Act: 1.2397. Min Act: -0.0000

Data Index: 630004 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.9738. Min Act: -0.0000

Data Index: 1022777 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.9132. Min Act: -0.0000

Data Index: 514603 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.8401. Min Act: -0.0000

Data Index: 466933 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.8691. Min Act: -0.0000

Data Index: 1248830 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.8022. Min Act: -0.0000

Data Index: 823484 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.7371. Min Act: -0.0000

Data Index: 407898 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.7249. Min Act: -0.0000

Data Index: 62933 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1276294 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.7533. Min Act: -0.0000

Data Index: 121347 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.7063. Min Act: 0.0001

Data Index: 1101696 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.7164. Min Act: -0.0000

Data Index: 234028 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.7374. Min Act: -0.0000

Data Index: 974674 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.6773. Min Act: -0.0000

Data Index: 865914 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.6593. Min Act: -0.0000

Data Index: 917567 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1343967 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.6683. Min Act: -0.0000

Data Index: 175910 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.6391. Min Act: -0.0000

Data Index: 796238 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.6095. Min Act: -0.0000

Data Index: 587515 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.6201. Min Act: -0.0000

Data Index: 69656 (C4 (Web Text))

Max Activating Token Index: 593