Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1698 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1021879 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0123. Min Act: -0.0003

Data Index: 644199 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0003

Data Index: 37456 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0121. Min Act: -0.0003

Data Index: 284973 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0117. Min Act: -0.0003

Data Index: 879636 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0119. Min Act: -0.0003

Data Index: 1336292 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0119. Min Act: -0.0003

Data Index: 549291 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0114. Min Act: -0.0003

Data Index: 1062333 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0114. Min Act: -0.0004

Data Index: 564825 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0114. Min Act: -0.0004

Data Index: 1134501 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0113. Min Act: -0.0004

Data Index: 773744 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0111. Min Act: -0.0003

Data Index: 402364 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0112. Min Act: -0.0003

Data Index: 851054 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0112. Min Act: -0.0003

Data Index: 897918 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0109. Min Act: -0.0003

Data Index: 1338301 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0110. Min Act: -0.0004

Data Index: 1057514 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0110. Min Act: -0.0004

Data Index: 925679 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0109. Min Act: -0.0004

Data Index: 326832 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0109. Min Act: -0.0004

Data Index: 101110 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0108. Min Act: -0.0003

Data Index: 303665 (C4 (Web Text))

Max Activating Token Index: 372