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

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

Neuron 1920 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: 0.0136. Min Range: -0.0136

Max Act: 0.0136. Min Act: -0.0006

Data Index: 840578 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1307578 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0125. Min Act: -0.0006

Data Index: 871773 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0124. Min Act: -0.0006

Data Index: 62316 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0123. Min Act: -0.0006

Data Index: 554310 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0121. Min Act: -0.0006

Data Index: 746054 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0123. Min Act: -0.0006

Data Index: 761355 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0118. Min Act: -0.0006

Data Index: 251646 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0121. Min Act: -0.0006

Data Index: 329447 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0121. Min Act: -0.0006

Data Index: 871721 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1110151 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0121. Min Act: -0.0006

Data Index: 162838 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0119. Min Act: -0.0006

Data Index: 262526 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0119. Min Act: -0.0006

Data Index: 178207 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0118. Min Act: -0.0006

Data Index: 776905 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1155291 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0119. Min Act: -0.0006

Data Index: 774394 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1183786 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1299496 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1125803 (C4 (Web Text))

Max Activating Token Index: 307