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

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

Neuron 877 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: 0.0155. Min Range: -0.0155

Max Act: 0.0155. Min Act: -0.0003

Data Index: 986178 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0148. Min Act: -0.0003

Data Index: 381963 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0142. Min Act: -0.0003

Data Index: 150231 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0137. Min Act: -0.0003

Data Index: 337308 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0137. Min Act: -0.0003

Data Index: 479337 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0131. Min Act: -0.0003

Data Index: 1135716 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0125. Min Act: -0.0004

Data Index: 132819 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0119. Min Act: -0.0003

Data Index: 679856 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0124. Min Act: -0.0003

Data Index: 724093 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0120. Min Act: -0.0004

Data Index: 850805 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0122. Min Act: -0.0003

Data Index: 674878 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1276250 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0121. Min Act: -0.0003

Data Index: 297705 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0124. Min Act: -0.0003

Data Index: 434649 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0120. Min Act: -0.0003

Data Index: 463209 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0119. Min Act: -0.0003

Data Index: 852431 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0119. Min Act: -0.0004

Data Index: 1297625 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0118. Min Act: -0.0003

Data Index: 1323474 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0117. Min Act: -0.0003

Data Index: 497301 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0117. Min Act: -0.0004

Data Index: 621774 (C4 (Web Text))

Max Activating Token Index: 212