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

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

Neuron 712 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: 0.0492. Min Range: -0.0492

Max Act: 0.0482. Min Act: -0.0006

Data Index: 319731 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0483. Min Act: -0.0006

Data Index: 652564 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0486. Min Act: -0.0006

Data Index: 1553260 (Python Code)

Max Activating Token Index: 595

Text #3

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0492. Min Act: -0.0006

Data Index: 953414 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0481. Min Act: -0.0006

Data Index: 124930 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0463. Min Act: -0.0005

Data Index: 970111 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0485. Min Act: -0.0006

Data Index: 1206724 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0445. Min Act: -0.0006

Data Index: 44293 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0444. Min Act: -0.0006

Data Index: 791680 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0453. Min Act: -0.0006

Data Index: 306755 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0441. Min Act: -0.0006

Data Index: 136380 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0451. Min Act: -0.0006

Data Index: 1348405 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0451. Min Act: -0.0006

Data Index: 255893 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0427. Min Act: -0.0006

Data Index: 708869 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0435. Min Act: -0.0006

Data Index: 1124478 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0440. Min Act: -0.0006

Data Index: 371028 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0438. Min Act: -0.0006

Data Index: 782324 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0420. Min Act: -0.0006

Data Index: 1542249 (Python Code)

Max Activating Token Index: 946

Text #18

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0436. Min Act: -0.0006

Data Index: 738006 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0417. Min Act: -0.0006

Data Index: 870432 (C4 (Web Text))

Max Activating Token Index: 888