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

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

Neuron 2066 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0132. Min Act: -0.0003

Data Index: 331337 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0128. Min Act: -0.0003

Data Index: 550749 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0127. Min Act: -0.0003

Data Index: 618 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0126. Min Act: -0.0003

Data Index: 1273222 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0128. Min Act: -0.0003

Data Index: 11763 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0125. Min Act: -0.0003

Data Index: 1284790 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0124. Min Act: -0.0003

Data Index: 765481 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0124. Min Act: -0.0003

Data Index: 720471 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0123. Min Act: -0.0003

Data Index: 203910 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0123. Min Act: -0.0003

Data Index: 1172224 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0123. Min Act: -0.0003

Data Index: 1333137 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0123. Min Act: -0.0003

Data Index: 725273 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1013345 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1202905 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0122. Min Act: -0.0003

Data Index: 558701 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0122. Min Act: -0.0003

Data Index: 977648 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0122. Min Act: -0.0002

Data Index: 951855 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0122. Min Act: -0.0003

Data Index: 586946 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0122. Min Act: -0.0003

Data Index: 930435 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0121. Min Act: -0.0003

Data Index: 796319 (C4 (Web Text))

Max Activating Token Index: 48