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

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

Neuron 2105 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0225. Min Act: -0.0000

Data Index: 362132 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0197. Min Act: -0.0000

Data Index: 153396 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0164. Min Act: -0.0000

Data Index: 988911 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0156. Min Act: -0.0000

Data Index: 1531649 (Python Code)

Max Activating Token Index: 333

Text #4

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0141. Min Act: -0.0000

Data Index: 745296 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0135. Min Act: -0.0000

Data Index: 1435917 (Python Code)

Max Activating Token Index: 297

Text #6

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0131. Min Act: -0.0000

Data Index: 321391 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0139. Min Act: -0.0000

Data Index: 1246052 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0125. Min Act: -0.0000

Data Index: 1419241 (Python Code)

Max Activating Token Index: 675

Text #9

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0127. Min Act: -0.0000

Data Index: 1490640 (Python Code)

Max Activating Token Index: 590

Text #10

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0128. Min Act: -0.0000

Data Index: 1309115 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0125. Min Act: -0.0000

Data Index: 607168 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0126. Min Act: -0.0000

Data Index: 1459574 (Python Code)

Max Activating Token Index: 54

Text #13

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0125. Min Act: -0.0000

Data Index: 305101 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0125. Min Act: -0.0000

Data Index: 955623 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0119. Min Act: -0.0000

Data Index: 717396 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0122. Min Act: -0.0000

Data Index: 468081 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0123. Min Act: -0.0000

Data Index: 1507987 (Python Code)

Max Activating Token Index: 128

Text #18

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0123. Min Act: -0.0000

Data Index: 1507266 (Python Code)

Max Activating Token Index: 106

Text #19

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0114. Min Act: -0.0000

Data Index: 1423199 (Python Code)

Max Activating Token Index: 258