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

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

Neuron 2225 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0212. Min Act: -0.0004

Data Index: 441311 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0211. Min Act: -0.0004

Data Index: 1010728 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0207. Min Act: -0.0004

Data Index: 963681 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0174. Min Act: -0.0004

Data Index: 43056 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0175. Min Act: -0.0004

Data Index: 203998 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0174. Min Act: -0.0004

Data Index: 715802 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0198. Min Act: -0.0004

Data Index: 671879 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0175. Min Act: -0.0004

Data Index: 565587 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0168. Min Act: -0.0004

Data Index: 1057016 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0167. Min Act: -0.0004

Data Index: 719440 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0163. Min Act: -0.0004

Data Index: 652794 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0169. Min Act: -0.0004

Data Index: 342634 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0168. Min Act: -0.0004

Data Index: 23722 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0167. Min Act: -0.0004

Data Index: 497590 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0167. Min Act: -0.0004

Data Index: 658938 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0159. Min Act: -0.0004

Data Index: 777887 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0168. Min Act: -0.0004

Data Index: 568418 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0164. Min Act: -0.0004

Data Index: 648547 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0166. Min Act: -0.0004

Data Index: 1349386 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0158. Min Act: -0.0004

Data Index: 888830 (C4 (Web Text))

Max Activating Token Index: 21