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

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

Neuron 2898 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: 0.3183. Min Range: -0.3183

Max Act: 0.3183. Min Act: -0.0001

Data Index: 54403 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2933. Min Act: -0.0001

Data Index: 179449 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.3060. Min Act: -0.0001

Data Index: 70258 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2907. Min Act: -0.0001

Data Index: 210952 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2831. Min Act: -0.0001

Data Index: 436322 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2781. Min Act: -0.0001

Data Index: 69993 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2849. Min Act: -0.0001

Data Index: 146522 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2617. Min Act: -0.0001

Data Index: 621970 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2548. Min Act: -0.0001

Data Index: 842415 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2680. Min Act: -0.0001

Data Index: 744041 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2557. Min Act: -0.0001

Data Index: 337741 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2614. Min Act: -0.0001

Data Index: 19682 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2591. Min Act: -0.0001

Data Index: 743941 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2567. Min Act: -0.0001

Data Index: 830954 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2562. Min Act: -0.0001

Data Index: 582856 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2530. Min Act: -0.0001

Data Index: 613945 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2598. Min Act: -0.0001

Data Index: 728840 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2542. Min Act: -0.0001

Data Index: 246348 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2323. Min Act: -0.0001

Data Index: 536085 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2578. Min Act: -0.0001

Data Index: 917378 (C4 (Web Text))

Max Activating Token Index: 217