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

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

Neuron 825 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0147. Min Act: -0.0006

Data Index: 32164 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0131. Min Act: -0.0006

Data Index: 994538 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0130. Min Act: -0.0006

Data Index: 828609 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1211629 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0131. Min Act: -0.0006

Data Index: 865174 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0124. Min Act: -0.0005

Data Index: 296559 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0126. Min Act: -0.0006

Data Index: 216667 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0124. Min Act: -0.0005

Data Index: 138965 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0123. Min Act: -0.0005

Data Index: 700271 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0123. Min Act: -0.0006

Data Index: 397018 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0126. Min Act: -0.0006

Data Index: 947071 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0120. Min Act: -0.0005

Data Index: 1203571 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0118. Min Act: -0.0006

Data Index: 756337 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0119. Min Act: -0.0006

Data Index: 745503 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0117. Min Act: -0.0006

Data Index: 833517 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0120. Min Act: -0.0006

Data Index: 998077 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0114. Min Act: -0.0005

Data Index: 1331440 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0113. Min Act: -0.0005

Data Index: 214809 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0111. Min Act: -0.0006

Data Index: 458811 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0113. Min Act: -0.0006

Data Index: 283393 (C4 (Web Text))

Max Activating Token Index: 354