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

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

Neuron 646 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1522. Min Act: -0.0000

Data Index: 183751 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1480. Min Act: -0.0000

Data Index: 199563 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1388. Min Act: -0.0000

Data Index: 241965 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1355. Min Act: -0.0000

Data Index: 1216437 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1254. Min Act: -0.0000

Data Index: 187498 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1262. Min Act: -0.0000

Data Index: 946515 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1191. Min Act: -0.0000

Data Index: 978643 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1187. Min Act: -0.0000

Data Index: 596816 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1322701 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1186. Min Act: -0.0000

Data Index: 1263710 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1100. Min Act: -0.0000

Data Index: 669000 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1109. Min Act: -0.0000

Data Index: 15569 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1025. Min Act: -0.0000

Data Index: 676570 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1046. Min Act: -0.0000

Data Index: 199061 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1062. Min Act: -0.0000

Data Index: 310403 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1009. Min Act: -0.0000

Data Index: 144836 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1003. Min Act: -0.0000

Data Index: 566953 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.0995. Min Act: -0.0000

Data Index: 301431 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1284366 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1047. Min Act: -0.0000

Data Index: 1023549 (C4 (Web Text))

Max Activating Token Index: 196