Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1228 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1489. Min Act: -0.0005

Data Index: 54453 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1282. Min Act: -0.0005

Data Index: 755910 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1333. Min Act: -0.0005

Data Index: 1154813 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1255. Min Act: -0.0005

Data Index: 800964 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1201. Min Act: -0.0005

Data Index: 296600 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1270. Min Act: -0.0005

Data Index: 11439 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1198. Min Act: -0.0005

Data Index: 522608 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1200. Min Act: -0.0005

Data Index: 75517 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1162. Min Act: -0.0005

Data Index: 557820 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1166. Min Act: -0.0005

Data Index: 152929 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1074. Min Act: -0.0005

Data Index: 1148626 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1033. Min Act: -0.0005

Data Index: 935082 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1044. Min Act: -0.0005

Data Index: 511337 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.0860. Min Act: -0.0005

Data Index: 318830 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1135. Min Act: -0.0005

Data Index: 936068 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.0997. Min Act: -0.0005

Data Index: 529963 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1027. Min Act: -0.0005

Data Index: 1161189 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1012. Min Act: -0.0005

Data Index: 1268977 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1019. Min Act: -0.0005

Data Index: 1135833 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.0985. Min Act: -0.0005

Data Index: 51044 (C4 (Web Text))

Max Activating Token Index: 117