Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 585 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0156. Min Act: -0.0002

Data Index: 357554 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0140. Min Act: -0.0002

Data Index: 755753 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0137. Min Act: -0.0002

Data Index: 778790 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0143. Min Act: -0.0002

Data Index: 993508 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0131. Min Act: -0.0002

Data Index: 752129 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0136. Min Act: -0.0002

Data Index: 506020 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0129. Min Act: -0.0002

Data Index: 708986 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0121. Min Act: -0.0002

Data Index: 1128702 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0109. Min Act: -0.0002

Data Index: 850759 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0119. Min Act: -0.0002

Data Index: 746605 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0100. Min Act: -0.0002

Data Index: 512115 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0115. Min Act: -0.0002

Data Index: 98105 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0107. Min Act: -0.0002

Data Index: 1008187 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0099. Min Act: -0.0002

Data Index: 91091 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1246560 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1491895 (Python Code)

Max Activating Token Index: 493

Text #16

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0100. Min Act: -0.0002

Data Index: 976757 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0120. Min Act: -0.0002

Data Index: 253642 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0106. Min Act: -0.0002

Data Index: 381378 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0118. Min Act: -0.0002

Data Index: 552053 (C4 (Web Text))

Max Activating Token Index: 614