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

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

Neuron 1247 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: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1122454 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0126. Min Act: -0.0006

Data Index: 987408 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0124. Min Act: -0.0006

Data Index: 908975 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0118. Min Act: -0.0006

Data Index: 694592 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0119. Min Act: -0.0005

Data Index: 114359 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0113. Min Act: -0.0006

Data Index: 36872 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0115. Min Act: -0.0006

Data Index: 574227 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0114. Min Act: -0.0006

Data Index: 712097 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0116. Min Act: -0.0006

Data Index: 1311199 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0112. Min Act: -0.0006

Data Index: 918718 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0108. Min Act: -0.0006

Data Index: 1095425 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0111. Min Act: -0.0006

Data Index: 615386 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1084815 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0099. Min Act: -0.0006

Data Index: 574795 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1536658 (Python Code)

Max Activating Token Index: 335

Text #15

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1330179 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1180321 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1490775 (Python Code)

Max Activating Token Index: 494

Text #18

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0108. Min Act: -0.0006

Data Index: 300809 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0108. Min Act: -0.0006

Data Index: 1524649 (Python Code)

Max Activating Token Index: 79