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

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

Neuron 3814 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1049. Min Range: -4.1049

Max Act: 4.1049. Min Act: 0.0001

Data Index: 237206 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 4.1049. Min Range: -4.1049

Max Act: 3.9631. Min Act: -0.0000

Data Index: 1147568 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 4.1049. Min Range: -4.1049

Max Act: 3.8023. Min Act: 0.0001

Data Index: 337784 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 4.1049. Min Range: -4.1049

Max Act: 3.7299. Min Act: 0.0000

Data Index: 277310 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 4.1049. Min Range: -4.1049

Max Act: 3.4962. Min Act: -0.0000

Data Index: 1270012 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 4.1049. Min Range: -4.1049

Max Act: 3.5258. Min Act: -0.0000

Data Index: 753740 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 4.1049. Min Range: -4.1049

Max Act: 3.5136. Min Act: -0.0000

Data Index: 897889 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 4.1049. Min Range: -4.1049

Max Act: 3.6668. Min Act: 0.0001

Data Index: 95430 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 4.1049. Min Range: -4.1049

Max Act: 3.3143. Min Act: -0.0000

Data Index: 213152 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 4.1049. Min Range: -4.1049

Max Act: 3.5503. Min Act: -0.0000

Data Index: 926887 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 4.1049. Min Range: -4.1049

Max Act: 3.4707. Min Act: -0.0000

Data Index: 32893 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 4.1049. Min Range: -4.1049

Max Act: 3.0835. Min Act: -0.0000

Data Index: 461198 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 4.1049. Min Range: -4.1049

Max Act: 3.1832. Min Act: -0.0000

Data Index: 271747 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 4.1049. Min Range: -4.1049

Max Act: 3.1157. Min Act: -0.0000

Data Index: 807343 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 4.1049. Min Range: -4.1049

Max Act: 3.0880. Min Act: -0.0000

Data Index: 342583 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 4.1049. Min Range: -4.1049

Max Act: 2.8855. Min Act: -0.0000

Data Index: 1181903 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 4.1049. Min Range: -4.1049

Max Act: 2.6733. Min Act: -0.0000

Data Index: 872115 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 4.1049. Min Range: -4.1049

Max Act: 2.7512. Min Act: 0.0001

Data Index: 237449 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 4.1049. Min Range: -4.1049

Max Act: 2.7560. Min Act: -0.0000

Data Index: 231189 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 4.1049. Min Range: -4.1049

Max Act: 2.4562. Min Act: -0.0000

Data Index: 854615 (C4 (Web Text))

Max Activating Token Index: 88