Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1115 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1684. Min Act: -0.0004

Data Index: 811700 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1605. Min Act: -0.0004

Data Index: 94348 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1498. Min Act: -0.0004

Data Index: 766025 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1371. Min Act: -0.0004

Data Index: 1060527 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1364. Min Act: -0.0004

Data Index: 1072811 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1370. Min Act: -0.0004

Data Index: 1233843 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1307. Min Act: -0.0004

Data Index: 940247 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1310. Min Act: -0.0004

Data Index: 414846 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1208. Min Act: -0.0004

Data Index: 1252028 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1203. Min Act: -0.0004

Data Index: 432696 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1229. Min Act: -0.0004

Data Index: 846736 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1143. Min Act: -0.0004

Data Index: 182117 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1252. Min Act: -0.0004

Data Index: 1156400 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1197. Min Act: -0.0004

Data Index: 286721 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1341. Min Act: -0.0004

Data Index: 35058 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1330. Min Act: -0.0004

Data Index: 543594 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1215. Min Act: -0.0004

Data Index: 806263 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1172. Min Act: -0.0004

Data Index: 782454 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1169. Min Act: -0.0004

Data Index: 515257 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1247. Min Act: -0.0004

Data Index: 1070465 (C4 (Web Text))

Max Activating Token Index: 1023