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

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

Neuron 4510 in Layer 1

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: 1.5499. Min Range: -1.5499

Max Act: 1.5499. Min Act: -0.0002

Data Index: 1261826 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.4904. Min Act: -0.0002

Data Index: 337220 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.4996. Min Act: -0.0002

Data Index: 1254886 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.4651. Min Act: -0.0002

Data Index: 962205 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.3801. Min Act: -0.0003

Data Index: 320473 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.3269. Min Act: -0.0002

Data Index: 124273 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.2602. Min Act: -0.0002

Data Index: 1224832 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.2597. Min Act: -0.0002

Data Index: 878800 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.2331. Min Act: -0.0002

Data Index: 599434 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.1974. Min Act: -0.0002

Data Index: 544308 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.2151. Min Act: -0.0002

Data Index: 845260 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.2279. Min Act: -0.0002

Data Index: 705748 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.1861. Min Act: -0.0002

Data Index: 522203 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.1902. Min Act: -0.0002

Data Index: 1358767 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.1689. Min Act: -0.0002

Data Index: 1220199 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.1510. Min Act: -0.0002

Data Index: 715418 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.1651. Min Act: -0.0002

Data Index: 615018 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.1520. Min Act: -0.0002

Data Index: 92451 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.1238. Min Act: -0.0002

Data Index: 321356 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 1.5499. Min Range: -1.5499

Max Act: 1.1358. Min Act: -0.0002

Data Index: 998948 (C4 (Web Text))

Max Activating Token Index: 40