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

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

Neuron 3754 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2566. Min Range: -2.2566

Max Act: 2.2566. Min Act: -0.0000

Data Index: 1501739 (Python Code)

Max Activating Token Index: 916

Text #1

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.8174. Min Act: -0.0000

Data Index: 255887 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.5799. Min Act: -0.0000

Data Index: 1165858 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.3588. Min Act: -0.0000

Data Index: 147996 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.4046. Min Act: -0.0000

Data Index: 112730 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.4240. Min Act: -0.0000

Data Index: 1488944 (Python Code)

Max Activating Token Index: 104

Text #6

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.4962. Min Act: -0.0000

Data Index: 915416 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.3892. Min Act: -0.0000

Data Index: 862847 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.2516. Min Act: -0.0000

Data Index: 1073270 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.2119. Min Act: -0.0000

Data Index: 320812 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.1977. Min Act: -0.0000

Data Index: 244573 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.2669. Min Act: -0.0000

Data Index: 585113 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.2693. Min Act: -0.0000

Data Index: 778112 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.1874. Min Act: -0.0000

Data Index: 79369 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.3103. Min Act: -0.0000

Data Index: 1297573 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.2375. Min Act: -0.0000

Data Index: 1151912 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.2291. Min Act: -0.0000

Data Index: 221938 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.1597. Min Act: -0.0000

Data Index: 331107 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.2263. Min Act: -0.0000

Data Index: 1267977 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 2.2566. Min Range: -2.2566

Max Act: 1.1492. Min Act: -0.0000

Data Index: 1118679 (C4 (Web Text))

Max Activating Token Index: 268