Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3286 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0135. Min Act: -0.0003

Data Index: 1186637 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0134. Min Act: -0.0003

Data Index: 253899 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0132. Min Act: -0.0003

Data Index: 1199720 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0124. Min Act: -0.0003

Data Index: 46252 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0121. Min Act: -0.0003

Data Index: 486173 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0114. Min Act: -0.0003

Data Index: 1350736 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0119. Min Act: -0.0003

Data Index: 964416 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0115. Min Act: -0.0003

Data Index: 942896 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0118. Min Act: -0.0003

Data Index: 491884 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0117. Min Act: -0.0003

Data Index: 724479 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0124. Min Act: -0.0003

Data Index: 936944 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0114. Min Act: -0.0003

Data Index: 472427 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0114. Min Act: -0.0003

Data Index: 404999 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0109. Min Act: -0.0003

Data Index: 271643 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0102. Min Act: -0.0003

Data Index: 127445 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0105. Min Act: -0.0003

Data Index: 34546 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0099. Min Act: -0.0003

Data Index: 1527297 (Python Code)

Max Activating Token Index: 951

Text #17

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0107. Min Act: -0.0003

Data Index: 321333 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0102. Min Act: -0.0003

Data Index: 990794 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0104. Min Act: -0.0003

Data Index: 1256552 (C4 (Web Text))

Max Activating Token Index: 929