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

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

Neuron 5621 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.6486. Min Act: -0.0000

Data Index: 278962 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.4977. Min Act: -0.0000

Data Index: 320477 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.2963. Min Act: -0.0000

Data Index: 225010 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.2998. Min Act: -0.0000

Data Index: 272068 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.4376. Min Act: -0.0000

Data Index: 495427 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.2634. Min Act: -0.0000

Data Index: 1185577 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.3234. Min Act: -0.0000

Data Index: 40849 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1303. Min Act: -0.0000

Data Index: 432744 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1502. Min Act: -0.0000

Data Index: 117847 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1803. Min Act: -0.0000

Data Index: 1130600 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1428. Min Act: -0.0000

Data Index: 738435 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1031. Min Act: -0.0000

Data Index: 246707 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1314. Min Act: -0.0000

Data Index: 640969 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.0600. Min Act: -0.0000

Data Index: 493174 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1225. Min Act: -0.0000

Data Index: 814340 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1046. Min Act: -0.0000

Data Index: 1102832 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1435. Min Act: -0.0000

Data Index: 1022237 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.0865. Min Act: -0.0000

Data Index: 430664 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.0590. Min Act: -0.0000

Data Index: 1022392 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.0767. Min Act: -0.0000

Data Index: 1263672 (C4 (Web Text))

Max Activating Token Index: 683