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

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

Neuron 4450 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1132947 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0131. Min Act: -0.0002

Data Index: 897041 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1122671 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0092. Min Act: -0.0002

Data Index: 4476 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1045368 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0101. Min Act: -0.0002

Data Index: 244340 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0083. Min Act: -0.0002

Data Index: 1090639 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0088. Min Act: -0.0002

Data Index: 815001 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0090. Min Act: -0.0002

Data Index: 880915 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0094. Min Act: -0.0002

Data Index: 1003415 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1183395 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0086. Min Act: -0.0002

Data Index: 1335795 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0089. Min Act: -0.0002

Data Index: 158808 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0086. Min Act: -0.0002

Data Index: 614718 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0082. Min Act: -0.0002

Data Index: 121412 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0080. Min Act: -0.0002

Data Index: 92811 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0085. Min Act: -0.0002

Data Index: 102540 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0084. Min Act: -0.0002

Data Index: 599025 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0090. Min Act: -0.0002

Data Index: 970807 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0083. Min Act: -0.0002

Data Index: 209753 (C4 (Web Text))

Max Activating Token Index: 165