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

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

Neuron 1201 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0136. Min Act: -0.0003

Data Index: 554495 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0130. Min Act: -0.0002

Data Index: 1340980 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0128. Min Act: -0.0003

Data Index: 221516 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0127. Min Act: -0.0003

Data Index: 258003 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0124. Min Act: -0.0003

Data Index: 247142 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0124. Min Act: -0.0003

Data Index: 954654 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0122. Min Act: -0.0003

Data Index: 141441 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0124. Min Act: -0.0003

Data Index: 648065 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0121. Min Act: -0.0003

Data Index: 378378 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0119. Min Act: -0.0003

Data Index: 1129229 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0119. Min Act: -0.0003

Data Index: 1245862 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0118. Min Act: -0.0003

Data Index: 917416 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0117. Min Act: -0.0003

Data Index: 635306 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0116. Min Act: -0.0003

Data Index: 91559 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0113. Min Act: -0.0003

Data Index: 118889 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0115. Min Act: -0.0003

Data Index: 262308 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0112. Min Act: -0.0003

Data Index: 638879 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0112. Min Act: -0.0003

Data Index: 89029 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0112. Min Act: -0.0003

Data Index: 370635 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0112. Min Act: -0.0003

Data Index: 514053 (C4 (Web Text))

Max Activating Token Index: 446