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

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

Neuron 210 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: 0.0134. Min Range: -0.0134

Max Act: 0.0134. Min Act: -0.0006

Data Index: 154658 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1341204 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0006

Data Index: 329421 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0125. Min Act: -0.0006

Data Index: 600287 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0122. Min Act: -0.0006

Data Index: 256169 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1066702 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0118. Min Act: -0.0005

Data Index: 913513 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1352213 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1195261 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0117. Min Act: -0.0006

Data Index: 387227 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0119. Min Act: -0.0006

Data Index: 389341 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0116. Min Act: -0.0006

Data Index: 881391 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0116. Min Act: -0.0006

Data Index: 1210634 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0118. Min Act: -0.0005

Data Index: 633461 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0115. Min Act: -0.0006

Data Index: 663902 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0115. Min Act: -0.0006

Data Index: 735728 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0115. Min Act: -0.0006

Data Index: 170527 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0115. Min Act: -0.0006

Data Index: 389383 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1219983 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0113. Min Act: -0.0006

Data Index: 50328 (C4 (Web Text))

Max Activating Token Index: 588