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

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

Neuron 3860 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: 0.3797. Min Range: -0.3797

Max Act: 0.3797. Min Act: -0.0001

Data Index: 168119 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3751. Min Act: -0.0001

Data Index: 947725 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3409. Min Act: -0.0001

Data Index: 81608 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3400. Min Act: -0.0001

Data Index: 817415 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3274. Min Act: -0.0001

Data Index: 449146 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3410. Min Act: -0.0001

Data Index: 171915 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3375. Min Act: -0.0001

Data Index: 1272014 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3125. Min Act: -0.0001

Data Index: 1058828 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3205. Min Act: -0.0001

Data Index: 1154113 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3392. Min Act: -0.0001

Data Index: 600461 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3467. Min Act: -0.0001

Data Index: 1014461 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3325. Min Act: -0.0001

Data Index: 462075 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3078. Min Act: -0.0001

Data Index: 1050428 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3193. Min Act: -0.0001

Data Index: 730531 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3116. Min Act: -0.0001

Data Index: 67887 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3327. Min Act: -0.0001

Data Index: 946594 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2940. Min Act: -0.0001

Data Index: 1052248 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3007. Min Act: -0.0001

Data Index: 456964 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3012. Min Act: -0.0001

Data Index: 41452 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3126. Min Act: -0.0001

Data Index: 81975 (C4 (Web Text))

Max Activating Token Index: 785