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

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

Neuron 1559 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: 0.0191. Min Range: -0.0191

Max Act: 0.0191. Min Act: -0.0006

Data Index: 748323 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1041160 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0146. Min Act: -0.0006

Data Index: 292305 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0145. Min Act: -0.0006

Data Index: 618485 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0138. Min Act: -0.0006

Data Index: 796708 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0133. Min Act: -0.0006

Data Index: 822647 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0133. Min Act: -0.0006

Data Index: 694609 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0131. Min Act: -0.0006

Data Index: 382824 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0129. Min Act: -0.0006

Data Index: 410571 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1003672 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0124. Min Act: -0.0006

Data Index: 626004 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0127. Min Act: -0.0006

Data Index: 847987 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0127. Min Act: -0.0006

Data Index: 1294895 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1122179 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0128. Min Act: -0.0006

Data Index: 500573 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0127. Min Act: -0.0006

Data Index: 854595 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0127. Min Act: -0.0006

Data Index: 689386 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0118. Min Act: -0.0006

Data Index: 183718 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0127. Min Act: -0.0006

Data Index: 863915 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1045078 (C4 (Web Text))

Max Activating Token Index: 704