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

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

Neuron 511 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: 0.0166. Min Range: -0.0166

Max Act: 0.0166. Min Act: -0.0006

Data Index: 424215 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0147. Min Act: -0.0006

Data Index: 340119 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0132. Min Act: -0.0006

Data Index: 132579 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0130. Min Act: -0.0006

Data Index: 1145065 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0127. Min Act: -0.0006

Data Index: 119425 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0127. Min Act: -0.0006

Data Index: 1219128 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0130. Min Act: -0.0006

Data Index: 33245 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0130. Min Act: -0.0006

Data Index: 1520887 (Python Code)

Max Activating Token Index: 766

Text #8

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1362443 (Python Code)

Max Activating Token Index: 168

Text #9

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0126. Min Act: -0.0006

Data Index: 267372 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0127. Min Act: -0.0006

Data Index: 589041 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1098166 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0126. Min Act: -0.0006

Data Index: 236585 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1468207 (Python Code)

Max Activating Token Index: 172

Text #14

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1305448 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1542871 (Python Code)

Max Activating Token Index: 576

Text #16

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0118. Min Act: -0.0006

Data Index: 708490 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0116. Min Act: -0.0006

Data Index: 1639307 (Python Code)

Max Activating Token Index: 564

Text #18

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0117. Min Act: -0.0006

Data Index: 513732 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0116. Min Act: -0.0006

Data Index: 994633 (C4 (Web Text))

Max Activating Token Index: 589