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

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

Neuron 178 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.2042. Min Act: -0.0000

Data Index: 123566 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1713. Min Act: -0.0000

Data Index: 354029 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1589. Min Act: -0.0000

Data Index: 788384 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1483. Min Act: -0.0000

Data Index: 884684 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1365. Min Act: -0.0000

Data Index: 830993 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1307. Min Act: -0.0000

Data Index: 378503 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1381. Min Act: -0.0000

Data Index: 1119815 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1368. Min Act: -0.0000

Data Index: 278253 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1253. Min Act: -0.0000

Data Index: 163603 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1166. Min Act: -0.0000

Data Index: 1098394 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1235. Min Act: -0.0000

Data Index: 1209735 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1104352 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1189. Min Act: -0.0000

Data Index: 752183 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1185. Min Act: -0.0000

Data Index: 997788 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1222. Min Act: -0.0000

Data Index: 514769 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1152. Min Act: -0.0000

Data Index: 675326 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1231827 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1110. Min Act: -0.0000

Data Index: 152960 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1135. Min Act: -0.0000

Data Index: 1045904 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1075. Min Act: -0.0000

Data Index: 27170 (C4 (Web Text))

Max Activating Token Index: 967