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

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

Neuron 4778 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6218. Min Range: -1.6218

Max Act: 1.6218. Min Act: -0.0001

Data Index: 102164 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 1.6218. Min Range: -1.6218

Max Act: 1.4783. Min Act: -0.0001

Data Index: 1111705 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 1.6218. Min Range: -1.6218

Max Act: 1.3398. Min Act: -0.0001

Data Index: 145091 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 1.6218. Min Range: -1.6218

Max Act: 1.3259. Min Act: -0.0001

Data Index: 559610 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 1.6218. Min Range: -1.6218

Max Act: 1.2809. Min Act: -0.0001

Data Index: 173571 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 1.6218. Min Range: -1.6218

Max Act: 1.2179. Min Act: -0.0001

Data Index: 180625 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 1.6218. Min Range: -1.6218

Max Act: 1.1801. Min Act: -0.0001

Data Index: 1235864 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 1.6218. Min Range: -1.6218

Max Act: 1.0673. Min Act: -0.0001

Data Index: 191497 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 1.6218. Min Range: -1.6218

Max Act: 1.1196. Min Act: -0.0001

Data Index: 421358 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 1.6218. Min Range: -1.6218

Max Act: 1.1010. Min Act: -0.0001

Data Index: 485696 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 1.6218. Min Range: -1.6218

Max Act: 1.1792. Min Act: -0.0001

Data Index: 282318 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 1.6218. Min Range: -1.6218

Max Act: 0.9197. Min Act: -0.0001

Data Index: 251943 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 1.6218. Min Range: -1.6218

Max Act: 1.1797. Min Act: -0.0001

Data Index: 954485 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 1.6218. Min Range: -1.6218

Max Act: 1.0717. Min Act: -0.0001

Data Index: 634244 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 1.6218. Min Range: -1.6218

Max Act: 0.9915. Min Act: -0.0001

Data Index: 148591 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 1.6218. Min Range: -1.6218

Max Act: 1.0083. Min Act: -0.0001

Data Index: 818152 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 1.6218. Min Range: -1.6218

Max Act: 1.0698. Min Act: -0.0001

Data Index: 735049 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 1.6218. Min Range: -1.6218

Max Act: 1.0084. Min Act: -0.0001

Data Index: 1076494 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 1.6218. Min Range: -1.6218

Max Act: 0.9772. Min Act: -0.0001

Data Index: 1185324 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 1.6218. Min Range: -1.6218

Max Act: 1.0301. Min Act: -0.0001

Data Index: 838862 (C4 (Web Text))

Max Activating Token Index: 371