Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 837 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0500. Min Act: -0.0002

Data Index: 540528 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.1096. Min Act: -0.0002

Data Index: 198307 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0682. Min Act: -0.0002

Data Index: 339870 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9886. Min Act: -0.0002

Data Index: 431684 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8232. Min Act: -0.0002

Data Index: 642206 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8890. Min Act: -0.0002

Data Index: 298237 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8375. Min Act: -0.0002

Data Index: 1343133 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0007. Min Act: -0.0002

Data Index: 642820 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9132. Min Act: -0.0002

Data Index: 345628 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9366. Min Act: -0.0002

Data Index: 469128 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8997. Min Act: -0.0002

Data Index: 348935 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.7939. Min Act: -0.0002

Data Index: 660274 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8199. Min Act: -0.0002

Data Index: 810898 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8953. Min Act: -0.0002

Data Index: 779647 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8277. Min Act: -0.0002

Data Index: 1118670 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9771. Min Act: -0.0002

Data Index: 125830 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.7463. Min Act: -0.0002

Data Index: 441604 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.7981. Min Act: -0.0002

Data Index: 603751 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8318. Min Act: -0.0002

Data Index: 768932 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.7488. Min Act: -0.0002

Data Index: 805221 (C4 (Web Text))

Max Activating Token Index: 744