Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2362 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3721. Min Act: -0.0001

Data Index: 670866 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2938. Min Act: -0.0001

Data Index: 985223 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2878. Min Act: -0.0001

Data Index: 494669 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2951. Min Act: -0.0001

Data Index: 961055 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2899. Min Act: -0.0001

Data Index: 1096785 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2928. Min Act: -0.0001

Data Index: 76209 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2873. Min Act: -0.0001

Data Index: 1304106 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2821. Min Act: -0.0001

Data Index: 453587 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2817. Min Act: -0.0001

Data Index: 970259 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2680. Min Act: -0.0001

Data Index: 1297917 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2662. Min Act: -0.0001

Data Index: 484769 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2700. Min Act: -0.0001

Data Index: 538397 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2649. Min Act: -0.0001

Data Index: 1075174 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2639. Min Act: -0.0001

Data Index: 375894 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2592. Min Act: -0.0001

Data Index: 205178 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2591. Min Act: -0.0002

Data Index: 793101 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2640. Min Act: -0.0001

Data Index: 814878 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2536. Min Act: -0.0001

Data Index: 60910 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2526. Min Act: -0.0001

Data Index: 873408 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2584. Min Act: -0.0001

Data Index: 206651 (C4 (Web Text))

Max Activating Token Index: 211