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

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

Neuron 1929 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.4446. Min Act: -0.0001

Data Index: 1014453 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.4314. Min Act: -0.0001

Data Index: 682877 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.4402. Min Act: -0.0001

Data Index: 545512 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.4001. Min Act: -0.0001

Data Index: 1224213 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3888. Min Act: -0.0001

Data Index: 253794 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3906. Min Act: -0.0001

Data Index: 1158251 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3978. Min Act: -0.0001

Data Index: 1091126 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3892. Min Act: -0.0001

Data Index: 716087 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3815. Min Act: -0.0001

Data Index: 1290247 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3713. Min Act: -0.0001

Data Index: 400788 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3725. Min Act: -0.0001

Data Index: 676113 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3479. Min Act: -0.0001

Data Index: 33590 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3323. Min Act: -0.0001

Data Index: 578865 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3434. Min Act: -0.0001

Data Index: 385125 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3538. Min Act: -0.0001

Data Index: 153143 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3501. Min Act: -0.0001

Data Index: 224527 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3565. Min Act: -0.0001

Data Index: 627591 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3457. Min Act: -0.0001

Data Index: 662680 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3473. Min Act: -0.0001

Data Index: 750851 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3509. Min Act: -0.0001

Data Index: 1261759 (C4 (Web Text))

Max Activating Token Index: 152