Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2786 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1048261 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.1126. Min Act: -0.0001

Data Index: 757848 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.1088. Min Act: -0.0001

Data Index: 355225 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.1023. Min Act: -0.0001

Data Index: 496743 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.1047. Min Act: -0.0001

Data Index: 669524 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.1069. Min Act: -0.0001

Data Index: 1024736 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0977. Min Act: -0.0001

Data Index: 628379 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0943. Min Act: -0.0001

Data Index: 1248462 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.1019. Min Act: -0.0001

Data Index: 469810 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1451352 (Python Code)

Max Activating Token Index: 662

Text #10

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0771. Min Act: -0.0001

Data Index: 76249 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0852. Min Act: -0.0001

Data Index: 837003 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0844. Min Act: -0.0001

Data Index: 341340 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0839. Min Act: -0.0001

Data Index: 672696 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0976. Min Act: -0.0001

Data Index: 144802 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0922. Min Act: -0.0001

Data Index: 226497 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1153379 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1146447 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.1017. Min Act: -0.0001

Data Index: 473939 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0877. Min Act: -0.0001

Data Index: 603671 (C4 (Web Text))

Max Activating Token Index: 844