Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 911 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0191. Min Act: -0.0006

Data Index: 457399 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1595252 (Python Code)

Max Activating Token Index: 780

Text #2

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0159. Min Act: -0.0006

Data Index: 672755 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0148. Min Act: -0.0005

Data Index: 1526036 (Python Code)

Max Activating Token Index: 919

Text #4

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0142. Min Act: -0.0006

Data Index: 121207 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1568234 (Python Code)

Max Activating Token Index: 584

Text #6

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0141. Min Act: -0.0005

Data Index: 1423294 (Python Code)

Max Activating Token Index: 394

Text #7

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0139. Min Act: -0.0006

Data Index: 858883 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0138. Min Act: -0.0005

Data Index: 1457664 (Python Code)

Max Activating Token Index: 705

Text #9

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0138. Min Act: -0.0005

Data Index: 1587894 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1039568 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1380498 (Python Code)

Max Activating Token Index: 1007

Text #12

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0135. Min Act: -0.0005

Data Index: 1469663 (Python Code)

Max Activating Token Index: 1011

Text #13

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0137. Min Act: -0.0006

Data Index: 250355 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0132. Min Act: -0.0005

Data Index: 1554696 (Python Code)

Max Activating Token Index: 910

Text #15

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1299219 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0135. Min Act: -0.0005

Data Index: 1494174 (Python Code)

Max Activating Token Index: 194

Text #17

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1629732 (Python Code)

Max Activating Token Index: 977

Text #18

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0131. Min Act: -0.0005

Data Index: 1544202 (Python Code)

Max Activating Token Index: 531

Text #19

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0131. Min Act: -0.0006

Data Index: 990954 (C4 (Web Text))

Max Activating Token Index: 513