Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4642 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0178. Min Act: -0.0002

Data Index: 755836 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0174. Min Act: -0.0002

Data Index: 303114 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0164. Min Act: -0.0002

Data Index: 560335 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0155. Min Act: -0.0002

Data Index: 933088 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0152. Min Act: -0.0002

Data Index: 173138 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0152. Min Act: -0.0002

Data Index: 539325 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1148053 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0147. Min Act: -0.0002

Data Index: 920660 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0147. Min Act: -0.0002

Data Index: 530787 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1286423 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0146. Min Act: -0.0002

Data Index: 322668 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1223905 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0145. Min Act: -0.0002

Data Index: 650538 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0141. Min Act: -0.0002

Data Index: 830003 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0143. Min Act: -0.0002

Data Index: 775781 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1308899 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1063638 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0142. Min Act: -0.0002

Data Index: 648604 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0145. Min Act: -0.0002

Data Index: 639301 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0142. Min Act: -0.0002

Data Index: 592948 (C4 (Web Text))

Max Activating Token Index: 50