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

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

Neuron 3462 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: 4.7585. Min Range: -4.7585

Max Act: 4.7585. Min Act: -0.0000

Data Index: 458029 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 4.7585. Min Range: -4.7585

Max Act: 3.3103. Min Act: -0.0000

Data Index: 91864 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 4.7585. Min Range: -4.7585

Max Act: 3.3023. Min Act: -0.0000

Data Index: 751630 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 4.7585. Min Range: -4.7585

Max Act: 3.2345. Min Act: -0.0000

Data Index: 104208 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 4.7585. Min Range: -4.7585

Max Act: 2.8618. Min Act: -0.0000

Data Index: 139577 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 4.7585. Min Range: -4.7585

Max Act: 3.0360. Min Act: -0.0000

Data Index: 418695 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 4.7585. Min Range: -4.7585

Max Act: 3.1179. Min Act: -0.0000

Data Index: 1109588 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 4.7585. Min Range: -4.7585

Max Act: 2.9661. Min Act: -0.0000

Data Index: 352243 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 4.7585. Min Range: -4.7585

Max Act: 3.0898. Min Act: -0.0000

Data Index: 694064 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 4.7585. Min Range: -4.7585

Max Act: 2.8584. Min Act: -0.0000

Data Index: 199492 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 4.7585. Min Range: -4.7585

Max Act: 3.1634. Min Act: -0.0000

Data Index: 841235 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 4.7585. Min Range: -4.7585

Max Act: 2.6928. Min Act: -0.0000

Data Index: 625659 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 4.7585. Min Range: -4.7585

Max Act: 2.7603. Min Act: -0.0000

Data Index: 1155002 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 4.7585. Min Range: -4.7585

Max Act: 2.7431. Min Act: -0.0000

Data Index: 366465 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 4.7585. Min Range: -4.7585

Max Act: 2.9047. Min Act: -0.0000

Data Index: 945282 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 4.7585. Min Range: -4.7585

Max Act: 2.8628. Min Act: -0.0000

Data Index: 980276 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 4.7585. Min Range: -4.7585

Max Act: 2.9915. Min Act: -0.0000

Data Index: 321468 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 4.7585. Min Range: -4.7585

Max Act: 2.5674. Min Act: -0.0000

Data Index: 763381 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 4.7585. Min Range: -4.7585

Max Act: 2.4019. Min Act: -0.0000

Data Index: 1355311 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 4.7585. Min Range: -4.7585

Max Act: 3.1260. Min Act: -0.0000

Data Index: 1305500 (C4 (Web Text))

Max Activating Token Index: 953