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

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

Neuron 1798 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.3488. Min Act: -0.0001

Data Index: 78195 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.2659. Min Act: -0.0001

Data Index: 1189751 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.2686. Min Act: -0.0001

Data Index: 1141424 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.3091. Min Act: -0.0001

Data Index: 389692 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.1974. Min Act: -0.0001

Data Index: 1064576 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.2889. Min Act: -0.0001

Data Index: 130806 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.1373. Min Act: -0.0001

Data Index: 1172815 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.3787. Min Act: -0.0001

Data Index: 1109503 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.3413. Min Act: -0.0001

Data Index: 964319 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.1159. Min Act: -0.0001

Data Index: 297204 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.1687. Min Act: -0.0001

Data Index: 171930 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.2443. Min Act: -0.0001

Data Index: 1121483 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.1644. Min Act: -0.0001

Data Index: 560372 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.1976. Min Act: -0.0001

Data Index: 1098663 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.2129. Min Act: -0.0001

Data Index: 166387 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.1478. Min Act: -0.0001

Data Index: 1085971 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.0919. Min Act: -0.0001

Data Index: 186959 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.1176. Min Act: -0.0001

Data Index: 379989 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.1107. Min Act: -0.0001

Data Index: 1033368 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.1408. Min Act: -0.0001

Data Index: 1019261 (C4 (Web Text))

Max Activating Token Index: 540