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

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

Neuron 1547 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: 0.3019. Min Range: -0.3019

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1061332 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2535. Min Act: -0.0001

Data Index: 7879 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2237. Min Act: -0.0000

Data Index: 612591 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2330. Min Act: -0.0000

Data Index: 224742 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2365. Min Act: -0.0001

Data Index: 1279664 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2283. Min Act: -0.0000

Data Index: 547326 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2236. Min Act: -0.0000

Data Index: 74969 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2240. Min Act: -0.0001

Data Index: 80695 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.1937. Min Act: -0.0000

Data Index: 383787 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.1963. Min Act: -0.0001

Data Index: 180584 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2163. Min Act: -0.0000

Data Index: 686459 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.1992. Min Act: -0.0000

Data Index: 423405 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.1844. Min Act: -0.0001

Data Index: 1321330 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.1953. Min Act: -0.0001

Data Index: 362302 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.1943. Min Act: -0.0000

Data Index: 475174 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.1925. Min Act: -0.0000

Data Index: 85236 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.1930. Min Act: -0.0000

Data Index: 832335 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2004. Min Act: -0.0001

Data Index: 1158647 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1310979 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.1698. Min Act: -0.0000

Data Index: 990754 (C4 (Web Text))

Max Activating Token Index: 514