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

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

Neuron 3362 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.3045. Min Act: -0.0001

Data Index: 1307505 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2986. Min Act: -0.0001

Data Index: 367231 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2766. Min Act: -0.0001

Data Index: 351058 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2869. Min Act: -0.0001

Data Index: 468037 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2654. Min Act: -0.0001

Data Index: 1304728 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2703. Min Act: -0.0001

Data Index: 1159465 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2780. Min Act: -0.0001

Data Index: 1288508 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2847. Min Act: -0.0001

Data Index: 761708 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2509. Min Act: -0.0001

Data Index: 1170668 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2794. Min Act: -0.0001

Data Index: 84372 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2633. Min Act: -0.0001

Data Index: 892819 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2502. Min Act: -0.0001

Data Index: 168915 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2634. Min Act: -0.0001

Data Index: 310780 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2460. Min Act: -0.0001

Data Index: 510201 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2722. Min Act: -0.0001

Data Index: 655002 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2647. Min Act: -0.0001

Data Index: 62458 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2640. Min Act: -0.0001

Data Index: 216622 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2516. Min Act: -0.0001

Data Index: 1214456 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2674. Min Act: -0.0001

Data Index: 1136115 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2672. Min Act: -0.0001

Data Index: 1156462 (C4 (Web Text))

Max Activating Token Index: 1010