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

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

Neuron 19 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1762. Min Act: -0.0001

Data Index: 473238 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1386. Min Act: -0.0001

Data Index: 28490 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1386. Min Act: -0.0001

Data Index: 1287266 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1348552 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1247. Min Act: -0.0001

Data Index: 513850 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1251. Min Act: -0.0001

Data Index: 728642 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1237. Min Act: -0.0001

Data Index: 6864 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1291. Min Act: -0.0001

Data Index: 938578 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1218. Min Act: -0.0001

Data Index: 793591 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1190. Min Act: -0.0001

Data Index: 918406 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1145. Min Act: -0.0001

Data Index: 446388 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1120. Min Act: -0.0001

Data Index: 126511 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1214. Min Act: -0.0001

Data Index: 276491 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1127. Min Act: -0.0001

Data Index: 1181424 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1152. Min Act: -0.0001

Data Index: 804598 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1159. Min Act: -0.0001

Data Index: 251467 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1130. Min Act: -0.0001

Data Index: 148949 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1166. Min Act: -0.0001

Data Index: 1287213 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1150. Min Act: -0.0001

Data Index: 534112 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1310411 (C4 (Web Text))

Max Activating Token Index: 904