Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2019 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0169. Min Act: -0.0006

Data Index: 1105975 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0168. Min Act: -0.0006

Data Index: 236875 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0161. Min Act: -0.0006

Data Index: 667425 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0153. Min Act: -0.0006

Data Index: 42525 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0156. Min Act: -0.0006

Data Index: 1249839 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0149. Min Act: -0.0006

Data Index: 829920 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0155. Min Act: -0.0006

Data Index: 663543 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0153. Min Act: -0.0006

Data Index: 297886 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0150. Min Act: -0.0006

Data Index: 65227 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1223870 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1091864 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1306288 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0151. Min Act: -0.0006

Data Index: 1148824 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1043608 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0143. Min Act: -0.0006

Data Index: 22018 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0145. Min Act: -0.0005

Data Index: 863563 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0135. Min Act: -0.0006

Data Index: 286632 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1011659 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0143. Min Act: -0.0006

Data Index: 690887 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0145. Min Act: -0.0006

Data Index: 280865 (C4 (Web Text))

Max Activating Token Index: 816