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

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

Neuron 639 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0149. Min Act: -0.0003

Data Index: 866279 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0128. Min Act: -0.0003

Data Index: 569848 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0131. Min Act: -0.0003

Data Index: 1203094 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0128. Min Act: -0.0003

Data Index: 989328 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0112. Min Act: -0.0003

Data Index: 311865 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0117. Min Act: -0.0003

Data Index: 39720 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0125. Min Act: -0.0003

Data Index: 302289 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0121. Min Act: -0.0003

Data Index: 1053245 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0091. Min Act: -0.0003

Data Index: 374095 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0114. Min Act: -0.0003

Data Index: 355630 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0110. Min Act: -0.0003

Data Index: 744274 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0130. Min Act: -0.0003

Data Index: 15001 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1123152 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0108. Min Act: -0.0003

Data Index: 51221 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0114. Min Act: -0.0003

Data Index: 543465 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0115. Min Act: -0.0003

Data Index: 996710 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0105. Min Act: -0.0003

Data Index: 479867 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0103. Min Act: -0.0003

Data Index: 503751 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0109. Min Act: -0.0003

Data Index: 504201 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0110. Min Act: -0.0003

Data Index: 95565 (C4 (Web Text))

Max Activating Token Index: 166