Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1597 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0115. Min Act: -0.0005

Data Index: 1076078 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0114. Min Act: -0.0006

Data Index: 348500 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0108. Min Act: -0.0005

Data Index: 831839 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0113. Min Act: -0.0005

Data Index: 1093213 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0106. Min Act: -0.0005

Data Index: 789534 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0109. Min Act: -0.0005

Data Index: 436113 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0108. Min Act: -0.0005

Data Index: 767768 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0109. Min Act: -0.0005

Data Index: 83655 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0104. Min Act: -0.0005

Data Index: 1315325 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0102. Min Act: -0.0006

Data Index: 604784 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0104. Min Act: -0.0005

Data Index: 185578 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0105. Min Act: -0.0005

Data Index: 178692 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0105. Min Act: -0.0005

Data Index: 375607 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0105. Min Act: -0.0006

Data Index: 363404 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0102. Min Act: -0.0005

Data Index: 358586 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0104. Min Act: -0.0005

Data Index: 560528 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0107. Min Act: -0.0005

Data Index: 523934 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0104. Min Act: -0.0005

Data Index: 704560 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0106. Min Act: -0.0005

Data Index: 818074 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0104. Min Act: -0.0005

Data Index: 1160981 (C4 (Web Text))

Max Activating Token Index: 852