Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1701 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1254. Min Act: -0.0003

Data Index: 1052245 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1227. Min Act: -0.0003

Data Index: 1067480 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1164. Min Act: -0.0003

Data Index: 630146 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1138. Min Act: -0.0003

Data Index: 1164639 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1165. Min Act: -0.0004

Data Index: 858875 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1003. Min Act: -0.0004

Data Index: 1157191 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1049. Min Act: -0.0003

Data Index: 704434 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1013. Min Act: -0.0003

Data Index: 968890 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0969. Min Act: -0.0003

Data Index: 216826 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0963. Min Act: -0.0004

Data Index: 260281 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1060. Min Act: -0.0003

Data Index: 340390 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0971. Min Act: -0.0003

Data Index: 423744 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0962. Min Act: -0.0003

Data Index: 107351 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0967. Min Act: -0.0003

Data Index: 442361 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0956. Min Act: -0.0003

Data Index: 108985 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0952. Min Act: -0.0003

Data Index: 1270681 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0947. Min Act: -0.0004

Data Index: 705947 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0944. Min Act: -0.0003

Data Index: 772612 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0940. Min Act: -0.0003

Data Index: 513633 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0907. Min Act: -0.0003

Data Index: 1343957 (C4 (Web Text))

Max Activating Token Index: 1003