Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 560 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0138. Min Act: -0.0005

Data Index: 818679 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0135. Min Act: -0.0006

Data Index: 945910 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0137. Min Act: -0.0005

Data Index: 737975 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1112152 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0133. Min Act: -0.0005

Data Index: 199106 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0128. Min Act: -0.0005

Data Index: 835675 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0126. Min Act: -0.0005

Data Index: 1246561 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0121. Min Act: -0.0005

Data Index: 599242 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1077347 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0120. Min Act: -0.0005

Data Index: 914740 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0118. Min Act: -0.0005

Data Index: 355054 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0116. Min Act: -0.0005

Data Index: 730146 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0113. Min Act: -0.0005

Data Index: 645069 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0114. Min Act: -0.0005

Data Index: 528246 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0114. Min Act: -0.0005

Data Index: 1345401 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0113. Min Act: -0.0006

Data Index: 1350897 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0112. Min Act: -0.0006

Data Index: 967526 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0112. Min Act: -0.0005

Data Index: 14902 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0109. Min Act: -0.0005

Data Index: 308699 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0113. Min Act: -0.0005

Data Index: 514553 (C4 (Web Text))

Max Activating Token Index: 69