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

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

Neuron 3595 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.3042. Min Act: -0.0000

Data Index: 468175 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.3274. Min Act: -0.0000

Data Index: 993966 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.3087. Min Act: -0.0000

Data Index: 927790 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2794. Min Act: -0.0000

Data Index: 499909 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2760. Min Act: -0.0000

Data Index: 629269 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.3043. Min Act: -0.0000

Data Index: 112007 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2782. Min Act: -0.0000

Data Index: 904783 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1143770 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2790. Min Act: -0.0000

Data Index: 959952 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2787. Min Act: -0.0000

Data Index: 302442 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2715. Min Act: -0.0000

Data Index: 613304 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2610. Min Act: -0.0000

Data Index: 458217 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2727. Min Act: -0.0000

Data Index: 518222 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2758. Min Act: -0.0000

Data Index: 475405 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2713. Min Act: -0.0000

Data Index: 200267 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2640. Min Act: -0.0000

Data Index: 458746 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2652. Min Act: -0.0000

Data Index: 334328 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2509. Min Act: -0.0000

Data Index: 668496 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2474. Min Act: -0.0000

Data Index: 393983 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2463. Min Act: -0.0000

Data Index: 1103623 (C4 (Web Text))

Max Activating Token Index: 194