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

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

Neuron 309 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: 2.1512. Min Range: -2.1512

Max Act: 2.1512. Min Act: -0.0000

Data Index: 66875 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 2.1512. Min Range: -2.1512

Max Act: 2.0055. Min Act: -0.0000

Data Index: 154523 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.9278. Min Act: -0.0001

Data Index: 1242810 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.7722. Min Act: -0.0000

Data Index: 66199 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.8519. Min Act: -0.0000

Data Index: 37864 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.6597. Min Act: -0.0001

Data Index: 1262277 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.6955. Min Act: -0.0001

Data Index: 896719 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.6578. Min Act: -0.0001

Data Index: 697960 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.5727. Min Act: -0.0000

Data Index: 1136972 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.6083. Min Act: -0.0000

Data Index: 1156410 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.6014. Min Act: -0.0001

Data Index: 657596 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.6959. Min Act: -0.0001

Data Index: 1191169 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.6061. Min Act: -0.0001

Data Index: 625232 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.5810. Min Act: -0.0000

Data Index: 88263 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.5695. Min Act: -0.0000

Data Index: 572993 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.5514. Min Act: -0.0000

Data Index: 125939 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.5426. Min Act: -0.0001

Data Index: 350735 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.3716. Min Act: -0.0000

Data Index: 1190885 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.4884. Min Act: -0.0000

Data Index: 346182 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.4332. Min Act: -0.0000

Data Index: 497432 (C4 (Web Text))

Max Activating Token Index: 77