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

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

Neuron 2978 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: 0.3129. Min Range: -0.3129

Max Act: 0.3129. Min Act: -0.0004

Data Index: 510186 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2940. Min Act: -0.0004

Data Index: 1025354 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2651. Min Act: -0.0004

Data Index: 139734 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2551. Min Act: -0.0004

Data Index: 127360 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.1979. Min Act: -0.0004

Data Index: 50509 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.1593. Min Act: -0.0004

Data Index: 37905 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.1456. Min Act: -0.0004

Data Index: 1329142 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.1442. Min Act: -0.0004

Data Index: 1017734 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.1433. Min Act: -0.0004

Data Index: 1175129 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.1540. Min Act: -0.0004

Data Index: 1101093 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.1658. Min Act: -0.0004

Data Index: 67368 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.1302. Min Act: -0.0004

Data Index: 1284647 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.1397. Min Act: -0.0004

Data Index: 527328 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.1482. Min Act: -0.0004

Data Index: 963818 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.1303. Min Act: -0.0004

Data Index: 240798 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.1669. Min Act: -0.0004

Data Index: 1269250 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.1379. Min Act: -0.0004

Data Index: 667714 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.1265. Min Act: -0.0004

Data Index: 1112370 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.1351. Min Act: -0.0004

Data Index: 305840 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.1298. Min Act: -0.0004

Data Index: 445427 (C4 (Web Text))

Max Activating Token Index: 1023