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

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

Neuron 2973 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: 0.1085. Min Range: -0.1085

Max Act: 0.1085. Min Act: -0.0002

Data Index: 227707 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0847. Min Act: -0.0002

Data Index: 40618 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0994. Min Act: -0.0002

Data Index: 584551 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0952. Min Act: -0.0002

Data Index: 513057 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1026. Min Act: -0.0002

Data Index: 1070491 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0776. Min Act: -0.0002

Data Index: 791592 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0893. Min Act: -0.0002

Data Index: 996988 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0938. Min Act: -0.0002

Data Index: 205146 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1079112 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0781. Min Act: -0.0002

Data Index: 334991 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1253810 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0817. Min Act: -0.0002

Data Index: 230216 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1091170 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0734. Min Act: -0.0002

Data Index: 708089 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0824. Min Act: -0.0002

Data Index: 584415 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0731. Min Act: -0.0002

Data Index: 139760 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0785. Min Act: -0.0002

Data Index: 99955 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0804. Min Act: -0.0002

Data Index: 606384 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0741. Min Act: -0.0002

Data Index: 507866 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1050793 (C4 (Web Text))

Max Activating Token Index: 803