Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2301 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0210. Min Act: -0.0003

Data Index: 108964 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0192. Min Act: -0.0003

Data Index: 946858 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0156. Min Act: -0.0003

Data Index: 356457 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0155. Min Act: -0.0003

Data Index: 96751 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0134. Min Act: -0.0003

Data Index: 968607 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0137. Min Act: -0.0003

Data Index: 1071990 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0146. Min Act: -0.0003

Data Index: 1278991 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0136. Min Act: -0.0003

Data Index: 468469 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0143. Min Act: -0.0003

Data Index: 155508 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0128. Min Act: -0.0003

Data Index: 857460 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0141. Min Act: -0.0003

Data Index: 1190526 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0152. Min Act: -0.0003

Data Index: 609155 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0142. Min Act: -0.0003

Data Index: 523200 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0138. Min Act: -0.0003

Data Index: 146430 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0134. Min Act: -0.0003

Data Index: 346391 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0116. Min Act: -0.0003

Data Index: 1178247 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0135. Min Act: -0.0003

Data Index: 99172 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0142. Min Act: -0.0003

Data Index: 304823 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0133. Min Act: -0.0003

Data Index: 110430 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0136. Min Act: -0.0003

Data Index: 1116778 (C4 (Web Text))

Max Activating Token Index: 159