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

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

Neuron 992 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: 0.2636. Min Range: -0.2636

Max Act: 0.2636. Min Act: -0.0005

Data Index: 1512460 (Python Code)

Max Activating Token Index: 885

Text #1

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2446. Min Act: -0.0005

Data Index: 1477070 (Python Code)

Max Activating Token Index: 421

Text #2

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2309. Min Act: -0.0005

Data Index: 1559376 (Python Code)

Max Activating Token Index: 957

Text #3

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2249. Min Act: -0.0005

Data Index: 1465935 (Python Code)

Max Activating Token Index: 589

Text #4

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2289. Min Act: -0.0005

Data Index: 1375554 (Python Code)

Max Activating Token Index: 684

Text #5

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2175. Min Act: -0.0005

Data Index: 1653477 (Python Code)

Max Activating Token Index: 359

Text #6

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2239. Min Act: -0.0005

Data Index: 1544233 (Python Code)

Max Activating Token Index: 267

Text #7

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2254. Min Act: -0.0005

Data Index: 1625253 (Python Code)

Max Activating Token Index: 164

Text #8

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2217. Min Act: -0.0005

Data Index: 1540630 (Python Code)

Max Activating Token Index: 883

Text #9

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2208. Min Act: -0.0005

Data Index: 1499930 (Python Code)

Max Activating Token Index: 561

Text #10

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2136. Min Act: -0.0005

Data Index: 1593161 (Python Code)

Max Activating Token Index: 911

Text #11

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2159. Min Act: -0.0005

Data Index: 1448825 (Python Code)

Max Activating Token Index: 809

Text #12

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.1997. Min Act: -0.0005

Data Index: 1498612 (Python Code)

Max Activating Token Index: 912

Text #13

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2149. Min Act: -0.0005

Data Index: 1619230 (Python Code)

Max Activating Token Index: 453

Text #14

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2148. Min Act: -0.0005

Data Index: 1432664 (Python Code)

Max Activating Token Index: 908

Text #15

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2149. Min Act: -0.0005

Data Index: 1486838 (Python Code)

Max Activating Token Index: 594

Text #16

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2160. Min Act: -0.0005

Data Index: 1590114 (Python Code)

Max Activating Token Index: 621

Text #17

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2131. Min Act: -0.0005

Data Index: 1504877 (Python Code)

Max Activating Token Index: 832

Text #18

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2135. Min Act: -0.0005

Data Index: 1529873 (Python Code)

Max Activating Token Index: 654

Text #19

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2036. Min Act: -0.0005

Data Index: 1554573 (Python Code)

Max Activating Token Index: 130