Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 41 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0186. Min Act: -0.0005

Data Index: 177771 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0167. Min Act: -0.0005

Data Index: 1223459 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0163. Min Act: -0.0005

Data Index: 1160212 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0161. Min Act: -0.0005

Data Index: 1230298 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0161. Min Act: -0.0005

Data Index: 606492 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0156. Min Act: -0.0006

Data Index: 589941 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0155. Min Act: -0.0005

Data Index: 183734 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0150. Min Act: -0.0005

Data Index: 708683 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0149. Min Act: -0.0005

Data Index: 868590 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0149. Min Act: -0.0005

Data Index: 70832 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0148. Min Act: -0.0005

Data Index: 569448 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0145. Min Act: -0.0005

Data Index: 887206 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0139. Min Act: -0.0005

Data Index: 1268344 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0142. Min Act: -0.0005

Data Index: 1087425 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0145. Min Act: -0.0005

Data Index: 1428 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0141. Min Act: -0.0005

Data Index: 522058 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0140. Min Act: -0.0005

Data Index: 1111165 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0139. Min Act: -0.0005

Data Index: 1333614 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0139. Min Act: -0.0005

Data Index: 1161130 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0134. Min Act: -0.0005

Data Index: 290398 (C4 (Web Text))

Max Activating Token Index: 390