Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4494 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0132. Min Act: -0.0002

Data Index: 155183 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0132. Min Act: -0.0002

Data Index: 148678 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0128. Min Act: -0.0002

Data Index: 715779 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1093055 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0121. Min Act: -0.0002

Data Index: 1230599 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1096717 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0121. Min Act: -0.0002

Data Index: 281750 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0111. Min Act: -0.0002

Data Index: 561839 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0112. Min Act: -0.0002

Data Index: 280509 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0135. Min Act: -0.0002

Data Index: 627864 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0128. Min Act: -0.0002

Data Index: 734866 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0125. Min Act: -0.0002

Data Index: 408998 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0117. Min Act: -0.0002

Data Index: 118974 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0127. Min Act: -0.0002

Data Index: 266756 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0117. Min Act: -0.0002

Data Index: 522569 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0105. Min Act: -0.0002

Data Index: 859542 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0084. Min Act: -0.0002

Data Index: 1106892 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0103. Min Act: -0.0002

Data Index: 17704 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0107. Min Act: -0.0002

Data Index: 689875 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0107. Min Act: -0.0002

Data Index: 581380 (C4 (Web Text))

Max Activating Token Index: 486