Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3552 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0134. Min Act: -0.0000

Data Index: 760277 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0107. Min Act: -0.0000

Data Index: 1406249 (Python Code)

Max Activating Token Index: 100

Text #2

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0103. Min Act: -0.0000

Data Index: 257789 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0102. Min Act: -0.0000

Data Index: 34798 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0092. Min Act: -0.0000

Data Index: 1329015 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0091. Min Act: -0.0000

Data Index: 379871 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0087. Min Act: -0.0000

Data Index: 1265799 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0089. Min Act: -0.0000

Data Index: 1642701 (Python Code)

Max Activating Token Index: 98

Text #8

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0081. Min Act: -0.0000

Data Index: 1412974 (Python Code)

Max Activating Token Index: 138

Text #9

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0083. Min Act: -0.0000

Data Index: 431802 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0082. Min Act: -0.0000

Data Index: 1277149 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0081. Min Act: -0.0000

Data Index: 828295 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0088. Min Act: -0.0000

Data Index: 882406 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0083. Min Act: -0.0000

Data Index: 717793 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0085. Min Act: -0.0000

Data Index: 199076 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0082. Min Act: -0.0000

Data Index: 903297 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0077. Min Act: -0.0000

Data Index: 641814 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0079. Min Act: -0.0000

Data Index: 41842 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0080. Min Act: -0.0000

Data Index: 614032 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0076. Min Act: -0.0000

Data Index: 222090 (C4 (Web Text))

Max Activating Token Index: 169