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

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

Neuron 1231 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0668. Min Act: -0.0002

Data Index: 726660 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0584. Min Act: -0.0003

Data Index: 123570 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0506. Min Act: -0.0003

Data Index: 219116 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0536. Min Act: -0.0003

Data Index: 731451 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0525. Min Act: -0.0003

Data Index: 287510 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0489. Min Act: -0.0003

Data Index: 70515 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0519. Min Act: -0.0003

Data Index: 1104683 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0507. Min Act: -0.0003

Data Index: 594256 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0528. Min Act: -0.0003

Data Index: 1478963 (Python Code)

Max Activating Token Index: 627

Text #9

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0525. Min Act: -0.0003

Data Index: 1639924 (Python Code)

Max Activating Token Index: 528

Text #10

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0502. Min Act: -0.0003

Data Index: 1568658 (Python Code)

Max Activating Token Index: 322

Text #11

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1445508 (Python Code)

Max Activating Token Index: 452

Text #12

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0494. Min Act: -0.0004

Data Index: 223003 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0485. Min Act: -0.0003

Data Index: 1411989 (Python Code)

Max Activating Token Index: 604

Text #14

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1582085 (Python Code)

Max Activating Token Index: 889

Text #15

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0483. Min Act: -0.0003

Data Index: 146410 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0477. Min Act: -0.0004

Data Index: 25521 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1356206 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1433114 (Python Code)

Max Activating Token Index: 354

Text #19

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0475. Min Act: -0.0003

Data Index: 493984 (C4 (Web Text))

Max Activating Token Index: 611