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

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

Neuron 3182 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: 1.8772. Min Range: -1.8772

Max Act: 1.8772. Min Act: -0.0000

Data Index: 344428 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.7420. Min Act: -0.0000

Data Index: 38444 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.6035. Min Act: -0.0000

Data Index: 759144 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.5856. Min Act: -0.0000

Data Index: 431017 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.5037. Min Act: -0.0000

Data Index: 1266045 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.3886. Min Act: -0.0000

Data Index: 409930 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.4959. Min Act: -0.0000

Data Index: 48007 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.4090. Min Act: -0.0000

Data Index: 150093 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.4442. Min Act: -0.0000

Data Index: 1332056 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.3801. Min Act: -0.0000

Data Index: 325925 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.4822. Min Act: -0.0000

Data Index: 107978 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.4182. Min Act: -0.0000

Data Index: 594137 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.3456. Min Act: -0.0000

Data Index: 937240 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.3603. Min Act: -0.0000

Data Index: 692415 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.3084. Min Act: -0.0000

Data Index: 406814 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.2943. Min Act: -0.0000

Data Index: 729617 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.3503. Min Act: -0.0000

Data Index: 333898 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.2962. Min Act: -0.0000

Data Index: 442144 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.2740. Min Act: -0.0000

Data Index: 1008766 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.2878. Min Act: -0.0000

Data Index: 1034217 (C4 (Web Text))

Max Activating Token Index: 54