Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 600 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.7087. Min Act: -0.0001

Data Index: 1314464 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.6107. Min Act: -0.0001

Data Index: 175967 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.6246. Min Act: -0.0001

Data Index: 513773 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.5953. Min Act: -0.0001

Data Index: 677069 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.5440. Min Act: -0.0001

Data Index: 381501 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.5334. Min Act: -0.0001

Data Index: 1228133 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.5515. Min Act: -0.0001

Data Index: 982183 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.5554. Min Act: -0.0001

Data Index: 1077619 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.5459. Min Act: -0.0001

Data Index: 1228395 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.5159. Min Act: -0.0001

Data Index: 1018720 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.5055. Min Act: -0.0001

Data Index: 903425 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.5469. Min Act: -0.0001

Data Index: 1127123 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.5108. Min Act: -0.0001

Data Index: 83809 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.4993. Min Act: -0.0001

Data Index: 82334 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.5142. Min Act: -0.0001

Data Index: 793100 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.5144. Min Act: -0.0001

Data Index: 1082560 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.4981. Min Act: -0.0001

Data Index: 700502 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.4902. Min Act: -0.0001

Data Index: 741048 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.5063. Min Act: -0.0001

Data Index: 96040 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.5223. Min Act: -0.0001

Data Index: 421248 (C4 (Web Text))

Max Activating Token Index: 450