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

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

Neuron 35 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: 0.0122. Min Range: -0.0122

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1536846 (Python Code)

Max Activating Token Index: 386

Text #1

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0101. Min Act: -0.0002

Data Index: 214005 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1481643 (Python Code)

Max Activating Token Index: 568

Text #3

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0105. Min Act: -0.0002

Data Index: 53132 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1088186 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0099. Min Act: -0.0002

Data Index: 1393711 (Python Code)

Max Activating Token Index: 85

Text #6

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1429930 (Python Code)

Max Activating Token Index: 646

Text #7

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0122. Min Act: -0.0002

Data Index: 788414 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1484919 (Python Code)

Max Activating Token Index: 434

Text #9

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0110. Min Act: -0.0002

Data Index: 1605570 (Python Code)

Max Activating Token Index: 349

Text #10

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1552481 (Python Code)

Max Activating Token Index: 363

Text #11

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0104. Min Act: -0.0002

Data Index: 663540 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1048924 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1465074 (Python Code)

Max Activating Token Index: 580

Text #14

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0109. Min Act: -0.0002

Data Index: 1202951 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0108. Min Act: -0.0002

Data Index: 1630058 (Python Code)

Max Activating Token Index: 134

Text #16

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0096. Min Act: -0.0002

Data Index: 220581 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1005345 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0100. Min Act: -0.0002

Data Index: 149568 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0101. Min Act: -0.0002

Data Index: 317860 (C4 (Web Text))

Max Activating Token Index: 26