Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3272 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0131. Min Act: -0.0002

Data Index: 425844 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1262531 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0128. Min Act: -0.0002

Data Index: 66340 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1074883 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0127. Min Act: -0.0002

Data Index: 271692 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1595438 (Python Code)

Max Activating Token Index: 21

Text #6

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1506312 (Python Code)

Max Activating Token Index: 745

Text #7

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0126. Min Act: -0.0002

Data Index: 653726 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1049950 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0126. Min Act: -0.0002

Data Index: 866877 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1274358 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0126. Min Act: -0.0002

Data Index: 500463 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0125. Min Act: -0.0002

Data Index: 369985 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1251540 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0125. Min Act: -0.0002

Data Index: 72172 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1062011 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0125. Min Act: -0.0002

Data Index: 465594 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0124. Min Act: -0.0002

Data Index: 879571 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1296000 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1077668 (C4 (Web Text))

Max Activating Token Index: 787