Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1502 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0223. Min Act: -0.0001

Data Index: 226805 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0206. Min Act: -0.0001

Data Index: 1240917 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0188. Min Act: -0.0001

Data Index: 634910 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1328688 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0164. Min Act: -0.0001

Data Index: 1278852 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0172. Min Act: -0.0001

Data Index: 1009996 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0157. Min Act: -0.0001

Data Index: 1247371 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0175. Min Act: -0.0001

Data Index: 1196817 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0160. Min Act: -0.0001

Data Index: 169737 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0158. Min Act: -0.0001

Data Index: 938903 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0147. Min Act: -0.0001

Data Index: 1322115 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0153. Min Act: -0.0001

Data Index: 1472358 (Python Code)

Max Activating Token Index: 149

Text #12

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0167. Min Act: -0.0001

Data Index: 92576 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0142. Min Act: -0.0001

Data Index: 1221696 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0160. Min Act: -0.0001

Data Index: 1118112 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0131. Min Act: -0.0001

Data Index: 692534 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0148. Min Act: -0.0001

Data Index: 597689 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0141. Min Act: -0.0002

Data Index: 171254 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0115. Min Act: -0.0001

Data Index: 1102995 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0142. Min Act: -0.0001

Data Index: 829994 (C4 (Web Text))

Max Activating Token Index: 967