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

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

Neuron 972 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0202. Min Act: -0.0001

Data Index: 1275402 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0172. Min Act: -0.0001

Data Index: 497769 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0182. Min Act: -0.0001

Data Index: 1154361 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0154. Min Act: -0.0001

Data Index: 788267 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0142. Min Act: -0.0001

Data Index: 307970 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0143. Min Act: -0.0001

Data Index: 892102 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0156. Min Act: -0.0001

Data Index: 553087 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0140. Min Act: -0.0001

Data Index: 70592 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0148. Min Act: -0.0001

Data Index: 1154846 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0132. Min Act: -0.0001

Data Index: 1065954 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0134. Min Act: -0.0001

Data Index: 993407 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0128. Min Act: -0.0001

Data Index: 637482 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0133. Min Act: -0.0001

Data Index: 799851 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0132. Min Act: -0.0001

Data Index: 638158 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0132. Min Act: -0.0001

Data Index: 957676 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0146. Min Act: -0.0001

Data Index: 1110706 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0123. Min Act: -0.0001

Data Index: 81810 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0130. Min Act: -0.0001

Data Index: 619581 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0120. Min Act: -0.0001

Data Index: 46357 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0124. Min Act: -0.0001

Data Index: 786045 (C4 (Web Text))

Max Activating Token Index: 948