Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1098 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0180. Min Act: -0.0002

Data Index: 1268814 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0162. Min Act: -0.0002

Data Index: 913466 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0160. Min Act: -0.0002

Data Index: 371001 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1426033 (Python Code)

Max Activating Token Index: 212

Text #4

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0155. Min Act: -0.0001

Data Index: 679759 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0150. Min Act: -0.0002

Data Index: 585090 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1497186 (Python Code)

Max Activating Token Index: 100

Text #7

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1320046 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1621324 (Python Code)

Max Activating Token Index: 295

Text #9

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1534009 (Python Code)

Max Activating Token Index: 618

Text #10

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0137. Min Act: -0.0003

Data Index: 223138 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0133. Min Act: -0.0002

Data Index: 668991 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0135. Min Act: -0.0001

Data Index: 1270361 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0133. Min Act: -0.0001

Data Index: 186124 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1171429 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1242768 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0128. Min Act: -0.0002

Data Index: 985536 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0129. Min Act: -0.0002

Data Index: 684866 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0129. Min Act: -0.0001

Data Index: 1536961 (Python Code)

Max Activating Token Index: 547

Text #19

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0133. Min Act: -0.0002

Data Index: 522356 (C4 (Web Text))

Max Activating Token Index: 929