Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 690 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0108. Min Act: -0.0001

Data Index: 1430365 (Python Code)

Max Activating Token Index: 558

Text #1

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0113. Min Act: -0.0001

Data Index: 1123986 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0107. Min Act: -0.0001

Data Index: 1356942 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0110. Min Act: -0.0001

Data Index: 1212899 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0102. Min Act: -0.0000

Data Index: 652523 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0094. Min Act: -0.0001

Data Index: 395596 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0084. Min Act: -0.0001

Data Index: 598369 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0098. Min Act: -0.0001

Data Index: 734533 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0092. Min Act: -0.0001

Data Index: 172336 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0088. Min Act: -0.0001

Data Index: 433693 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0097. Min Act: -0.0001

Data Index: 1350920 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0100. Min Act: -0.0001

Data Index: 156020 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0092. Min Act: -0.0001

Data Index: 749031 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0081. Min Act: -0.0001

Data Index: 1361270 (Python Code)

Max Activating Token Index: 275

Text #14

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0084. Min Act: -0.0001

Data Index: 406089 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0095. Min Act: -0.0001

Data Index: 576975 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0091. Min Act: -0.0001

Data Index: 837140 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0087. Min Act: -0.0001

Data Index: 815475 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0082. Min Act: -0.0000

Data Index: 1199990 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0089. Min Act: -0.0001

Data Index: 1129412 (C4 (Web Text))

Max Activating Token Index: 97