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

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

Neuron 545 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1616. Min Act: -0.0001

Data Index: 1183700 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1031878 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1299. Min Act: -0.0001

Data Index: 723941 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1228. Min Act: -0.0001

Data Index: 808905 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1276. Min Act: -0.0001

Data Index: 82305 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1237. Min Act: -0.0001

Data Index: 714921 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1272. Min Act: -0.0001

Data Index: 120786 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1326. Min Act: -0.0001

Data Index: 82641 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1193. Min Act: -0.0001

Data Index: 13912 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1227. Min Act: -0.0001

Data Index: 656106 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1231676 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1237. Min Act: -0.0001

Data Index: 286305 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1228. Min Act: -0.0001

Data Index: 746282 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1192. Min Act: -0.0001

Data Index: 1215253 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1135. Min Act: -0.0001

Data Index: 1192449 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1192. Min Act: -0.0001

Data Index: 523791 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1221. Min Act: -0.0001

Data Index: 474709 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1137. Min Act: -0.0001

Data Index: 1057743 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1085556 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1120. Min Act: -0.0001

Data Index: 770189 (C4 (Web Text))

Max Activating Token Index: 600