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

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

Neuron 1548 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: 0.3658. Min Range: -0.3658

Max Act: 0.3658. Min Act: -0.0000

Data Index: 452220 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3551. Min Act: -0.0000

Data Index: 198848 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3387. Min Act: -0.0000

Data Index: 739456 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3273. Min Act: -0.0000

Data Index: 79733 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3333. Min Act: -0.0000

Data Index: 1107396 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3174. Min Act: -0.0000

Data Index: 756588 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2932. Min Act: -0.0000

Data Index: 405441 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2982. Min Act: -0.0000

Data Index: 128303 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3097. Min Act: -0.0000

Data Index: 733570 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3093. Min Act: -0.0000

Data Index: 1183272 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3072. Min Act: -0.0000

Data Index: 680998 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3007. Min Act: -0.0000

Data Index: 80699 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1092763 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1350581 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1222847 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2995. Min Act: -0.0000

Data Index: 140029 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2867. Min Act: -0.0000

Data Index: 947633 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2950. Min Act: -0.0000

Data Index: 868035 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2945. Min Act: -0.0000

Data Index: 530934 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1146540 (C4 (Web Text))

Max Activating Token Index: 581