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

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

Neuron 1634 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: 0.0126. Min Range: -0.0126

Max Act: 0.0124. Min Act: -0.0006

Data Index: 294255 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0006

Data Index: 684898 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1300126 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1083256 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0119. Min Act: -0.0006

Data Index: 182063 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0006

Data Index: 425217 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1335066 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1310889 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0006

Data Index: 636946 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0006

Data Index: 838043 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0114. Min Act: -0.0006

Data Index: 32475 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0114. Min Act: -0.0006

Data Index: 362296 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0114. Min Act: -0.0006

Data Index: 122936 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0006

Data Index: 727317 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0006

Data Index: 946179 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1206268 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0006

Data Index: 264074 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0113. Min Act: -0.0006

Data Index: 384806 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1279200 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0112. Min Act: -0.0006

Data Index: 421239 (C4 (Web Text))

Max Activating Token Index: 855