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

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

Neuron 4690 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.3112. Min Act: -0.0000

Data Index: 941298 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.3069. Min Act: -0.0000

Data Index: 1054671 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2718. Min Act: -0.0000

Data Index: 664358 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2719. Min Act: -0.0000

Data Index: 1077576 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1637. Min Act: -0.0000

Data Index: 242772 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1589. Min Act: -0.0000

Data Index: 1053922 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1397. Min Act: -0.0000

Data Index: 1317148 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1502. Min Act: -0.0000

Data Index: 642910 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1399. Min Act: -0.0000

Data Index: 221631 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1434. Min Act: -0.0000

Data Index: 735620 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1371. Min Act: -0.0000

Data Index: 359568 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1320. Min Act: -0.0000

Data Index: 253702 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1334. Min Act: -0.0000

Data Index: 1095837 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1343. Min Act: -0.0000

Data Index: 577573 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1261832 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1251. Min Act: -0.0000

Data Index: 101965 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1294. Min Act: -0.0000

Data Index: 505373 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1324. Min Act: -0.0000

Data Index: 265996 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1275988 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1177255 (C4 (Web Text))

Max Activating Token Index: 130