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

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

Neuron 297 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: 0.0168. Min Range: -0.0168

Max Act: 0.0168. Min Act: -0.0006

Data Index: 273592 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0150. Min Act: -0.0006

Data Index: 715826 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1276676 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0140. Min Act: -0.0006

Data Index: 390620 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0131. Min Act: -0.0006

Data Index: 976656 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0124. Min Act: -0.0006

Data Index: 203530 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0128. Min Act: -0.0006

Data Index: 286735 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1144553 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0126. Min Act: -0.0006

Data Index: 71992 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1312375 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1356628 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0121. Min Act: -0.0006

Data Index: 837132 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0116. Min Act: -0.0006

Data Index: 635964 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1157827 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1261455 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0117. Min Act: -0.0006

Data Index: 232727 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0115. Min Act: -0.0006

Data Index: 122608 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1297482 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0113. Min Act: -0.0006

Data Index: 1266549 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1256751 (C4 (Web Text))

Max Activating Token Index: 8