Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 629 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: -0.0006

Data Index: 630797 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0536. Min Act: -0.0006

Data Index: 929753 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0453. Min Act: -0.0006

Data Index: 340339 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0426. Min Act: -0.0006

Data Index: 1096453 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0418. Min Act: -0.0006

Data Index: 1171688 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0426. Min Act: -0.0006

Data Index: 155988 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0462. Min Act: -0.0006

Data Index: 480473 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0420. Min Act: -0.0006

Data Index: 569576 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0375. Min Act: -0.0006

Data Index: 1270909 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0381. Min Act: -0.0006

Data Index: 577048 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0397. Min Act: -0.0006

Data Index: 1010030 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0405. Min Act: -0.0006

Data Index: 1136142 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0378. Min Act: -0.0006

Data Index: 486429 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0420. Min Act: -0.0006

Data Index: 1299262 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0432. Min Act: -0.0006

Data Index: 1168222 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0390. Min Act: -0.0006

Data Index: 218957 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0423. Min Act: -0.0006

Data Index: 1118058 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0412. Min Act: -0.0006

Data Index: 134131 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0421. Min Act: -0.0006

Data Index: 628240 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0402. Min Act: -0.0006

Data Index: 228769 (C4 (Web Text))

Max Activating Token Index: 529