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

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

Neuron 4918 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3340. Min Act: -0.0001

Data Index: 99915 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3174. Min Act: -0.0001

Data Index: 806633 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3046. Min Act: -0.0001

Data Index: 353010 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3105. Min Act: -0.0001

Data Index: 806643 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3022. Min Act: -0.0001

Data Index: 1354293 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2897. Min Act: -0.0001

Data Index: 1202014 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2876. Min Act: -0.0001

Data Index: 1265789 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2804. Min Act: -0.0001

Data Index: 1327554 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2789. Min Act: -0.0001

Data Index: 1050893 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2801. Min Act: -0.0001

Data Index: 976277 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2766. Min Act: -0.0001

Data Index: 1194936 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2746. Min Act: -0.0001

Data Index: 1253749 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2732. Min Act: -0.0001

Data Index: 1215188 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2738. Min Act: -0.0001

Data Index: 1003182 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2764. Min Act: -0.0001

Data Index: 859189 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2709. Min Act: -0.0001

Data Index: 1020297 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2671. Min Act: -0.0001

Data Index: 527197 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2696. Min Act: -0.0001

Data Index: 543469 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2628. Min Act: -0.0001

Data Index: 1315386 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2651. Min Act: -0.0001

Data Index: 1156974 (C4 (Web Text))

Max Activating Token Index: 391