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

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

Neuron 4148 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3959. Min Range: -4.3959

Max Act: 4.3959. Min Act: -0.0000

Data Index: 967752 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 4.3959. Min Range: -4.3959

Max Act: 4.0492. Min Act: -0.0000

Data Index: 603801 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 4.3959. Min Range: -4.3959

Max Act: 4.0216. Min Act: -0.0000

Data Index: 1081506 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 4.3959. Min Range: -4.3959

Max Act: 4.0543. Min Act: -0.0000

Data Index: 589662 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 4.3959. Min Range: -4.3959

Max Act: 3.5651. Min Act: -0.0000

Data Index: 618275 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 4.3959. Min Range: -4.3959

Max Act: 3.3718. Min Act: -0.0001

Data Index: 872928 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 4.3959. Min Range: -4.3959

Max Act: 3.2908. Min Act: -0.0000

Data Index: 1234259 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 4.3959. Min Range: -4.3959

Max Act: 3.7151. Min Act: -0.0001

Data Index: 1074755 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 4.3959. Min Range: -4.3959

Max Act: 3.3969. Min Act: -0.0000

Data Index: 2644 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 4.3959. Min Range: -4.3959

Max Act: 3.1831. Min Act: -0.0001

Data Index: 945270 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 4.3959. Min Range: -4.3959

Max Act: 3.0672. Min Act: -0.0000

Data Index: 1305132 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 4.3959. Min Range: -4.3959

Max Act: 3.3340. Min Act: -0.0000

Data Index: 753653 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 4.3959. Min Range: -4.3959

Max Act: 2.8707. Min Act: -0.0000

Data Index: 549432 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 4.3959. Min Range: -4.3959

Max Act: 3.1574. Min Act: -0.0000

Data Index: 754984 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 4.3959. Min Range: -4.3959

Max Act: 3.2011. Min Act: -0.0001

Data Index: 1165983 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 4.3959. Min Range: -4.3959

Max Act: 3.1856. Min Act: -0.0000

Data Index: 1079514 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 4.3959. Min Range: -4.3959

Max Act: 2.9851. Min Act: -0.0001

Data Index: 846150 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 4.3959. Min Range: -4.3959

Max Act: 3.1147. Min Act: -0.0000

Data Index: 49067 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 4.3959. Min Range: -4.3959

Max Act: 2.8333. Min Act: -0.0000

Data Index: 583441 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 4.3959. Min Range: -4.3959

Max Act: 3.1071. Min Act: -0.0000

Data Index: 762887 (C4 (Web Text))

Max Activating Token Index: 711