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

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

Neuron 1636 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1646. Min Act: -0.0002

Data Index: 141404 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1243. Min Act: -0.0003

Data Index: 367607 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1188. Min Act: -0.0003

Data Index: 1230131 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1136. Min Act: -0.0003

Data Index: 1201645 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1160. Min Act: -0.0003

Data Index: 798267 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1141. Min Act: -0.0003

Data Index: 467065 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1131. Min Act: -0.0003

Data Index: 89140 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1129. Min Act: -0.0003

Data Index: 978749 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1125. Min Act: -0.0003

Data Index: 549279 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1112. Min Act: -0.0003

Data Index: 202603 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1107. Min Act: -0.0003

Data Index: 307231 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1110. Min Act: -0.0003

Data Index: 820925 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1094. Min Act: -0.0003

Data Index: 701300 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1052. Min Act: -0.0002

Data Index: 386220 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1117. Min Act: -0.0003

Data Index: 148018 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1098. Min Act: -0.0003

Data Index: 1293925 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1043. Min Act: -0.0003

Data Index: 1197338 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1038. Min Act: -0.0003

Data Index: 670538 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1032. Min Act: -0.0002

Data Index: 185321 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1045. Min Act: -0.0003

Data Index: 1119248 (C4 (Web Text))

Max Activating Token Index: 391