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

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

Neuron 874 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0124. Min Act: -0.0006

Data Index: 672031 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0006

Data Index: 486794 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0109. Min Act: -0.0006

Data Index: 237319 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0108. Min Act: -0.0006

Data Index: 192951 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0112. Min Act: -0.0006

Data Index: 1152430 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0109. Min Act: -0.0006

Data Index: 272362 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0108. Min Act: -0.0006

Data Index: 515137 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0110. Min Act: -0.0006

Data Index: 541252 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0104. Min Act: -0.0006

Data Index: 30856 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0102. Min Act: -0.0006

Data Index: 995584 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0099. Min Act: -0.0006

Data Index: 205805 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0100. Min Act: -0.0006

Data Index: 595604 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1149721 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0096. Min Act: -0.0006

Data Index: 1097497 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0101. Min Act: -0.0006

Data Index: 238941 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0097. Min Act: -0.0006

Data Index: 636778 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0098. Min Act: -0.0006

Data Index: 584820 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0093. Min Act: -0.0006

Data Index: 495834 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0096. Min Act: -0.0006

Data Index: 1187845 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0095. Min Act: -0.0006

Data Index: 988762 (C4 (Web Text))

Max Activating Token Index: 59