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

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

Neuron 1928 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: 134324 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0128. Min Act: -0.0006

Data Index: 669880 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0131. Min Act: -0.0006

Data Index: 346817 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1020787 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1195588 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0121. Min Act: -0.0006

Data Index: 802333 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0120. Min Act: -0.0006

Data Index: 244779 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0119. Min Act: -0.0006

Data Index: 24671 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0118. Min Act: -0.0006

Data Index: 967581 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0115. Min Act: -0.0006

Data Index: 845653 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0114. Min Act: -0.0005

Data Index: 642470 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0113. Min Act: -0.0006

Data Index: 779515 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0111. Min Act: -0.0006

Data Index: 98245 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0110. Min Act: -0.0006

Data Index: 191452 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0111. Min Act: -0.0006

Data Index: 1030176 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0109. Min Act: -0.0006

Data Index: 942236 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1052619 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0109. Min Act: -0.0006

Data Index: 353615 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0109. Min Act: -0.0005

Data Index: 541799 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0108. Min Act: -0.0005

Data Index: 915982 (C4 (Web Text))

Max Activating Token Index: 801