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

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

Neuron 1120 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1341. Min Act: -0.0001

Data Index: 459832 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1211. Min Act: -0.0002

Data Index: 1032050 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1197. Min Act: -0.0002

Data Index: 185763 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1198. Min Act: -0.0001

Data Index: 1073195 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1191. Min Act: -0.0002

Data Index: 2234 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1180. Min Act: -0.0002

Data Index: 223010 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1129. Min Act: -0.0002

Data Index: 163556 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1110. Min Act: -0.0002

Data Index: 833662 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1122. Min Act: 0.0002

Data Index: 138073 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1137. Min Act: -0.0002

Data Index: 1332342 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1109. Min Act: 0.0001

Data Index: 671890 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1111. Min Act: -0.0001

Data Index: 165687 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1041. Min Act: -0.0002

Data Index: 1036008 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1082. Min Act: -0.0001

Data Index: 697941 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1097. Min Act: 0.0002

Data Index: 963359 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1061. Min Act: -0.0001

Data Index: 69098 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1050. Min Act: -0.0001

Data Index: 116384 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1043. Min Act: -0.0002

Data Index: 238056 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1068. Min Act: 0.0006

Data Index: 955874 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1031. Min Act: -0.0002

Data Index: 932649 (C4 (Web Text))

Max Activating Token Index: 442