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

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

Neuron 1873 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0141. Min Act: -0.0006

Data Index: 1331592 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0147. Min Act: -0.0006

Data Index: 412913 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1022722 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1044806 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0151. Min Act: -0.0006

Data Index: 307163 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0146. Min Act: -0.0006

Data Index: 171256 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0142. Min Act: -0.0006

Data Index: 1237052 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0127. Min Act: -0.0006

Data Index: 577503 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0146. Min Act: -0.0006

Data Index: 812029 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1418383 (Python Code)

Max Activating Token Index: 944

Text #10

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0122. Min Act: -0.0006

Data Index: 464898 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0139. Min Act: -0.0005

Data Index: 334449 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0140. Min Act: -0.0006

Data Index: 783861 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1226727 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0140. Min Act: -0.0006

Data Index: 911112 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0137. Min Act: -0.0006

Data Index: 682528 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0137. Min Act: -0.0006

Data Index: 426281 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1471543 (Python Code)

Max Activating Token Index: 328

Text #18

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0127. Min Act: -0.0006

Data Index: 132002 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0143. Min Act: -0.0006

Data Index: 431908 (C4 (Web Text))

Max Activating Token Index: 180