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

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

Neuron 1250 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: 0.0114. Min Range: -0.0114

Max Act: 0.0114. Min Act: -0.0006

Data Index: 804113 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0107. Min Act: -0.0006

Data Index: 6565 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0110. Min Act: -0.0006

Data Index: 443328 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1135364 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1299029 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1345234 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1034572 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0105. Min Act: -0.0006

Data Index: 283296 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1006634 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0100. Min Act: -0.0006

Data Index: 65564 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0105. Min Act: -0.0006

Data Index: 942138 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1314260 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1011578 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1157647 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0102. Min Act: -0.0006

Data Index: 90072 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0098. Min Act: -0.0006

Data Index: 530520 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0101. Min Act: -0.0006

Data Index: 631353 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0099. Min Act: -0.0006

Data Index: 414027 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1149189 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0097. Min Act: -0.0006

Data Index: 516831 (C4 (Web Text))

Max Activating Token Index: 618