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

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

Neuron 999 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: 0.3877. Min Range: -0.3877

Max Act: 0.3877. Min Act: -0.0001

Data Index: 1009811 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3389. Min Act: -0.0001

Data Index: 1034280 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3766. Min Act: -0.0001

Data Index: 226162 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3198. Min Act: -0.0001

Data Index: 564618 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3182. Min Act: -0.0001

Data Index: 1003172 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3377. Min Act: -0.0001

Data Index: 193650 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3148. Min Act: -0.0001

Data Index: 811733 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3220. Min Act: -0.0001

Data Index: 153990 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3098. Min Act: -0.0001

Data Index: 550236 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3132. Min Act: -0.0001

Data Index: 129830 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3125. Min Act: -0.0001

Data Index: 192998 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3207. Min Act: -0.0001

Data Index: 289919 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3112. Min Act: -0.0001

Data Index: 946317 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3124. Min Act: -0.0001

Data Index: 972920 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3013. Min Act: -0.0001

Data Index: 1067017 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3101. Min Act: -0.0001

Data Index: 890790 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.2934. Min Act: -0.0001

Data Index: 1151135 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3071. Min Act: -0.0001

Data Index: 890086 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3051. Min Act: -0.0001

Data Index: 706279 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.2707. Min Act: -0.0001

Data Index: 615043 (C4 (Web Text))

Max Activating Token Index: 933