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

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

Neuron 1840 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: 0.0164. Min Range: -0.0164

Max Act: 0.0164. Min Act: -0.0006

Data Index: 651056 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0147. Min Act: -0.0005

Data Index: 152822 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0140. Min Act: -0.0005

Data Index: 1255142 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0138. Min Act: -0.0005

Data Index: 955595 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0133. Min Act: -0.0005

Data Index: 170507 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0125. Min Act: -0.0005

Data Index: 1085619 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0122. Min Act: -0.0005

Data Index: 140229 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0122. Min Act: -0.0005

Data Index: 1105464 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0121. Min Act: -0.0005

Data Index: 720708 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0117. Min Act: -0.0005

Data Index: 970866 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0114. Min Act: -0.0005

Data Index: 40524 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0113. Min Act: -0.0005

Data Index: 124077 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1157407 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0111. Min Act: -0.0005

Data Index: 725567 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0109. Min Act: -0.0005

Data Index: 234036 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0111. Min Act: -0.0006

Data Index: 126528 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0108. Min Act: -0.0006

Data Index: 301676 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0105. Min Act: -0.0005

Data Index: 632592 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1235419 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0107. Min Act: -0.0005

Data Index: 864070 (C4 (Web Text))

Max Activating Token Index: 476