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

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

Neuron 1413 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: 0.1352. Min Range: -0.1352

Max Act: 0.1352. Min Act: -0.0001

Data Index: 1478333 (Python Code)

Max Activating Token Index: 878

Text #1

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1586676 (Python Code)

Max Activating Token Index: 472

Text #2

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1232. Min Act: -0.0001

Data Index: 1546205 (Python Code)

Max Activating Token Index: 1022

Text #3

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1426102 (Python Code)

Max Activating Token Index: 326

Text #4

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1102. Min Act: -0.0001

Data Index: 1458988 (Python Code)

Max Activating Token Index: 147

Text #5

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1167. Min Act: -0.0001

Data Index: 1519112 (Python Code)

Max Activating Token Index: 717

Text #6

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1370353 (Python Code)

Max Activating Token Index: 215

Text #7

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1272. Min Act: -0.0001

Data Index: 1486605 (Python Code)

Max Activating Token Index: 865

Text #8

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1144. Min Act: -0.0001

Data Index: 579827 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1487325 (Python Code)

Max Activating Token Index: 569

Text #10

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1549097 (Python Code)

Max Activating Token Index: 569

Text #11

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1446598 (Python Code)

Max Activating Token Index: 410

Text #12

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1200. Min Act: -0.0001

Data Index: 681081 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1159. Min Act: -0.0001

Data Index: 1452834 (Python Code)

Max Activating Token Index: 648

Text #14

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1655190 (Python Code)

Max Activating Token Index: 800

Text #15

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1100. Min Act: -0.0001

Data Index: 1575345 (Python Code)

Max Activating Token Index: 157

Text #16

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1137. Min Act: -0.0001

Data Index: 850157 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1099. Min Act: -0.0001

Data Index: 143746 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1134. Min Act: -0.0001

Data Index: 1505245 (Python Code)

Max Activating Token Index: 831

Text #19

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1457552 (Python Code)

Max Activating Token Index: 443