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

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

Neuron 2045 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.6878. Min Act: -0.0001

Data Index: 222757 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.4845. Min Act: -0.0000

Data Index: 580222 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.3992. Min Act: -0.0000

Data Index: 365406 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.4245. Min Act: -0.0001

Data Index: 992009 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.3962. Min Act: -0.0000

Data Index: 392990 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.4182. Min Act: -0.0000

Data Index: 772526 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1294121 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.4076. Min Act: -0.0001

Data Index: 1241352 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.4301. Min Act: -0.0000

Data Index: 820909 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.4047. Min Act: -0.0000

Data Index: 1253144 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.4512. Min Act: -0.0000

Data Index: 417068 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.4104. Min Act: -0.0000

Data Index: 262185 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.3837. Min Act: -0.0000

Data Index: 878412 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.3768. Min Act: -0.0000

Data Index: 914519 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.3711. Min Act: -0.0000

Data Index: 647560 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.3680. Min Act: -0.0000

Data Index: 341710 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.3768. Min Act: -0.0001

Data Index: 852326 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.3765. Min Act: -0.0000

Data Index: 524511 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.3769. Min Act: -0.0001

Data Index: 1288052 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.3273. Min Act: -0.0001

Data Index: 1328204 (C4 (Web Text))

Max Activating Token Index: 691