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

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

Neuron 1276 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: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0006

Data Index: 795606 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0140. Min Act: -0.0006

Data Index: 828952 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0141. Min Act: -0.0006

Data Index: 32308 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0131. Min Act: -0.0006

Data Index: 753385 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0133. Min Act: -0.0006

Data Index: 437123 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0126. Min Act: -0.0006

Data Index: 30517 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0121. Min Act: -0.0006

Data Index: 750246 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0124. Min Act: -0.0006

Data Index: 130451 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0121. Min Act: -0.0006

Data Index: 487984 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1209974 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0122. Min Act: -0.0006

Data Index: 106735 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0131. Min Act: -0.0006

Data Index: 194942 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0124. Min Act: -0.0006

Data Index: 666380 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0117. Min Act: -0.0006

Data Index: 547121 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1633053 (Python Code)

Max Activating Token Index: 670

Text #15

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1216057 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0117. Min Act: -0.0006

Data Index: 812875 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0117. Min Act: -0.0006

Data Index: 192996 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0119. Min Act: -0.0006

Data Index: 476497 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0124. Min Act: -0.0006

Data Index: 677165 (C4 (Web Text))

Max Activating Token Index: 967