Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1609 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0143. Min Act: -0.0005

Data Index: 454197 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0134. Min Act: -0.0005

Data Index: 286870 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0133. Min Act: -0.0005

Data Index: 138957 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0129. Min Act: -0.0005

Data Index: 914686 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0122. Min Act: -0.0005

Data Index: 1055572 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0117. Min Act: -0.0005

Data Index: 373979 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0118. Min Act: -0.0005

Data Index: 522498 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0114. Min Act: -0.0005

Data Index: 456376 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0116. Min Act: -0.0005

Data Index: 1406219 (Python Code)

Max Activating Token Index: 580

Text #9

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0116. Min Act: -0.0005

Data Index: 1128422 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0115. Min Act: -0.0005

Data Index: 23063 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1084426 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0115. Min Act: -0.0005

Data Index: 799317 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0116. Min Act: -0.0005

Data Index: 61060 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1100884 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0112. Min Act: -0.0005

Data Index: 505221 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0112. Min Act: -0.0005

Data Index: 208616 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0114. Min Act: -0.0005

Data Index: 1278797 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1064435 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0109. Min Act: -0.0005

Data Index: 185703 (C4 (Web Text))

Max Activating Token Index: 724