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

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

Neuron 1538 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: 0.1465. Min Range: -0.1465

Max Act: 0.1397. Min Act: -0.0001

Data Index: 723791 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1465. Min Act: -0.0001

Data Index: 914908 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1285. Min Act: -0.0001

Data Index: 430295 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1106. Min Act: -0.0001

Data Index: 944313 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1320. Min Act: -0.0001

Data Index: 1238756 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1060. Min Act: -0.0001

Data Index: 826303 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1132. Min Act: -0.0001

Data Index: 558865 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1254. Min Act: -0.0001

Data Index: 883060 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1246. Min Act: -0.0001

Data Index: 1203402 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1229. Min Act: -0.0001

Data Index: 1284034 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1235. Min Act: -0.0001

Data Index: 742242 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1143. Min Act: -0.0001

Data Index: 990483 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1161. Min Act: -0.0001

Data Index: 191447 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1115. Min Act: -0.0001

Data Index: 560568 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1140. Min Act: -0.0001

Data Index: 877697 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1215. Min Act: -0.0001

Data Index: 814544 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1018. Min Act: -0.0001

Data Index: 909474 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1102223 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1142. Min Act: -0.0001

Data Index: 685837 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1036. Min Act: -0.0001

Data Index: 345825 (C4 (Web Text))

Max Activating Token Index: 799