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

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

Neuron 3042 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: 1.2879. Min Range: -1.2879

Max Act: 1.2879. Min Act: -0.0000

Data Index: 1191484 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.2829. Min Act: -0.0000

Data Index: 396271 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.1819. Min Act: -0.0000

Data Index: 19216 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.2218. Min Act: -0.0000

Data Index: 710103 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.2566. Min Act: -0.0000

Data Index: 640406 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.1840. Min Act: -0.0000

Data Index: 1176157 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.1113. Min Act: -0.0000

Data Index: 319966 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.1467. Min Act: -0.0000

Data Index: 1026588 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.1457. Min Act: -0.0000

Data Index: 1284652 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.1363. Min Act: -0.0000

Data Index: 1058960 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.1978. Min Act: -0.0000

Data Index: 779943 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.1119. Min Act: -0.0000

Data Index: 853708 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.1029. Min Act: -0.0000

Data Index: 1117861 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.0937. Min Act: -0.0000

Data Index: 832545 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.0602. Min Act: -0.0000

Data Index: 106581 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.0923. Min Act: -0.0000

Data Index: 978286 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.0883. Min Act: -0.0000

Data Index: 196158 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.0499. Min Act: -0.0000

Data Index: 1305993 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.1172. Min Act: -0.0000

Data Index: 1322501 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 1.2879. Min Range: -1.2879

Max Act: 1.0844. Min Act: -0.0000

Data Index: 575149 (C4 (Web Text))

Max Activating Token Index: 619