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

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

Neuron 773 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: 1.5680. Min Range: -1.5680

Max Act: 1.4860. Min Act: -0.0000

Data Index: 508758 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.4097. Min Act: -0.0000

Data Index: 407071 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.5680. Min Act: -0.0000

Data Index: 1118491 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.3819. Min Act: -0.0000

Data Index: 177330 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.4652. Min Act: -0.0000

Data Index: 1283406 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.2832. Min Act: -0.0000

Data Index: 1070582 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.2678. Min Act: -0.0000

Data Index: 115307 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.3479. Min Act: -0.0000

Data Index: 73561 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.3119. Min Act: -0.0000

Data Index: 1180053 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.2945. Min Act: -0.0000

Data Index: 609168 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.2599. Min Act: -0.0000

Data Index: 1312429 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.1728. Min Act: -0.0000

Data Index: 864663 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.2341. Min Act: -0.0000

Data Index: 1233279 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.1438. Min Act: -0.0000

Data Index: 931987 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.2972. Min Act: -0.0000

Data Index: 1174017 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.2782. Min Act: -0.0000

Data Index: 195997 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.1994. Min Act: -0.0000

Data Index: 414997 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.1281. Min Act: -0.0000

Data Index: 630230 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.1908. Min Act: -0.0000

Data Index: 157746 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.1811. Min Act: -0.0000

Data Index: 1147733 (C4 (Web Text))

Max Activating Token Index: 454