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

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

Neuron 1656 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: 0.3684. Min Range: -0.3684

Max Act: 0.3007. Min Act: -0.0002

Data Index: 1026901 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.3407. Min Act: -0.0002

Data Index: 334377 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.3068. Min Act: -0.0002

Data Index: 1145161 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.3594. Min Act: -0.0002

Data Index: 220904 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.3684. Min Act: -0.0002

Data Index: 990256 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.3158. Min Act: -0.0002

Data Index: 446193 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.3123. Min Act: -0.0002

Data Index: 172325 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.3188. Min Act: -0.0002

Data Index: 185944 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.2969. Min Act: -0.0002

Data Index: 84843 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.3193. Min Act: -0.0002

Data Index: 762692 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.3082. Min Act: -0.0002

Data Index: 477666 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.3285. Min Act: -0.0002

Data Index: 85204 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.3119. Min Act: -0.0002

Data Index: 610751 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.2901. Min Act: -0.0002

Data Index: 858094 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.2588. Min Act: -0.0002

Data Index: 385072 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.3171. Min Act: -0.0002

Data Index: 978126 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.3175. Min Act: -0.0002

Data Index: 726619 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.3137. Min Act: -0.0002

Data Index: 547722 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.2826. Min Act: -0.0002

Data Index: 1087224 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.3684. Min Range: -0.3684

Max Act: 0.3027. Min Act: -0.0002

Data Index: 1056909 (C4 (Web Text))

Max Activating Token Index: 345