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

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

Neuron 4117 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.9061. Min Act: -0.0000

Data Index: 1033181 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.8291. Min Act: -0.0000

Data Index: 947385 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.6971. Min Act: -0.0000

Data Index: 508926 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.4900. Min Act: -0.0000

Data Index: 1174282 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1333880 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.5043. Min Act: -0.0000

Data Index: 743886 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.4869. Min Act: -0.0000

Data Index: 138316 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.4785. Min Act: -0.0000

Data Index: 625322 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1339810 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.4552. Min Act: -0.0000

Data Index: 410788 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.4214. Min Act: -0.0000

Data Index: 569582 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1026099 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1289496 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.4218. Min Act: -0.0000

Data Index: 668272 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.3920. Min Act: -0.0000

Data Index: 18786 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1069877 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1067934 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.3734. Min Act: -0.0000

Data Index: 720395 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.3715. Min Act: -0.0000

Data Index: 1333741 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.9061. Min Range: -0.9061

Max Act: 0.3610. Min Act: -0.0000

Data Index: 677600 (C4 (Web Text))

Max Activating Token Index: 873