Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1488 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2656. Min Act: -0.0000

Data Index: 228347 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1275839 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2569. Min Act: -0.0001

Data Index: 138994 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2572. Min Act: -0.0001

Data Index: 540793 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1002954 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1346387 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2653. Min Act: -0.0001

Data Index: 1019505 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1162115 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1205435 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2306. Min Act: -0.0000

Data Index: 1073693 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2387. Min Act: -0.0000

Data Index: 254647 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1179659 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2394. Min Act: -0.0000

Data Index: 359750 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2366. Min Act: -0.0000

Data Index: 970350 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2291. Min Act: -0.0000

Data Index: 845868 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2370. Min Act: -0.0001

Data Index: 986602 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2352. Min Act: -0.0000

Data Index: 176609 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2341. Min Act: -0.0000

Data Index: 968728 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1014600 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.2656. Min Range: -0.2656

Max Act: 0.2328. Min Act: -0.0001

Data Index: 763438 (C4 (Web Text))

Max Activating Token Index: 97