Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1498 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0445. Min Act: -0.0006

Data Index: 1097688 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0449. Min Act: -0.0006

Data Index: 999839 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0441. Min Act: -0.0006

Data Index: 109309 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0440. Min Act: -0.0006

Data Index: 693161 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0427. Min Act: -0.0006

Data Index: 499491 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0416. Min Act: -0.0006

Data Index: 1137116 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0410. Min Act: -0.0006

Data Index: 1316405 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0421. Min Act: -0.0006

Data Index: 805088 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0428. Min Act: -0.0006

Data Index: 320983 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0402. Min Act: -0.0006

Data Index: 206460 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0416. Min Act: -0.0006

Data Index: 846405 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0411. Min Act: -0.0006

Data Index: 150565 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0416. Min Act: -0.0006

Data Index: 467112 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0415. Min Act: -0.0006

Data Index: 293037 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0404. Min Act: -0.0006

Data Index: 614957 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0412. Min Act: -0.0006

Data Index: 26855 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0409. Min Act: -0.0006

Data Index: 829834 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0408. Min Act: -0.0006

Data Index: 934303 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0398. Min Act: -0.0006

Data Index: 330231 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0382. Min Act: -0.0006

Data Index: 183549 (C4 (Web Text))

Max Activating Token Index: 735