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

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

Neuron 4867 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6783. Min Range: -3.6783

Max Act: 3.6783. Min Act: -0.0000

Data Index: 1320 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 3.6783. Min Range: -3.6783

Max Act: 3.2126. Min Act: -0.0000

Data Index: 842389 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 3.6783. Min Range: -3.6783

Max Act: 3.3297. Min Act: -0.0000

Data Index: 644057 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 3.6783. Min Range: -3.6783

Max Act: 3.4100. Min Act: -0.0000

Data Index: 573963 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 3.6783. Min Range: -3.6783

Max Act: 3.1009. Min Act: -0.0000

Data Index: 963645 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 3.6783. Min Range: -3.6783

Max Act: 3.4378. Min Act: -0.0000

Data Index: 1336247 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 3.6783. Min Range: -3.6783

Max Act: 2.9591. Min Act: -0.0000

Data Index: 219558 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 3.6783. Min Range: -3.6783

Max Act: 2.9308. Min Act: -0.0000

Data Index: 1137163 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 3.6783. Min Range: -3.6783

Max Act: 3.0574. Min Act: -0.0000

Data Index: 1094355 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 3.6783. Min Range: -3.6783

Max Act: 3.0297. Min Act: -0.0000

Data Index: 256272 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 3.6783. Min Range: -3.6783

Max Act: 3.0462. Min Act: -0.0000

Data Index: 988877 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 3.6783. Min Range: -3.6783

Max Act: 3.0463. Min Act: -0.0000

Data Index: 378571 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 3.6783. Min Range: -3.6783

Max Act: 2.9095. Min Act: -0.0000

Data Index: 614129 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 3.6783. Min Range: -3.6783

Max Act: 3.1385. Min Act: -0.0000

Data Index: 1214276 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 3.6783. Min Range: -3.6783

Max Act: 2.7978. Min Act: -0.0000

Data Index: 1085134 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 3.6783. Min Range: -3.6783

Max Act: 2.9814. Min Act: -0.0000

Data Index: 390091 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 3.6783. Min Range: -3.6783

Max Act: 2.9348. Min Act: -0.0000

Data Index: 546907 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 3.6783. Min Range: -3.6783

Max Act: 2.9406. Min Act: -0.0000

Data Index: 279722 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 3.6783. Min Range: -3.6783

Max Act: 2.7976. Min Act: -0.0000

Data Index: 562637 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 3.6783. Min Range: -3.6783

Max Act: 2.9396. Min Act: -0.0000

Data Index: 1297181 (C4 (Web Text))

Max Activating Token Index: 793