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

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

Neuron 1782 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: 0.0143. Min Range: -0.0143

Max Act: 0.0142. Min Act: -0.0006

Data Index: 430708 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0143. Min Act: -0.0006

Data Index: 8420 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0132. Min Act: -0.0005

Data Index: 272550 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0132. Min Act: -0.0006

Data Index: 62260 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1104058 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1414861 (Python Code)

Max Activating Token Index: 661

Text #6

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0126. Min Act: -0.0005

Data Index: 875655 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0124. Min Act: -0.0006

Data Index: 619399 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0127. Min Act: -0.0006

Data Index: 1285564 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1332540 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0123. Min Act: -0.0006

Data Index: 595164 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0122. Min Act: -0.0006

Data Index: 570109 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0119. Min Act: -0.0006

Data Index: 933100 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0119. Min Act: -0.0005

Data Index: 89658 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0121. Min Act: -0.0006

Data Index: 328000 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1164073 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0120. Min Act: -0.0005

Data Index: 1980 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0115. Min Act: -0.0006

Data Index: 500902 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0118. Min Act: -0.0006

Data Index: 997118 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1249368 (C4 (Web Text))

Max Activating Token Index: 567