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

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

Neuron 1822 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0495. Min Act: -0.0005

Data Index: 857509 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0491. Min Act: -0.0005

Data Index: 948973 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0465. Min Act: -0.0005

Data Index: 743009 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0467. Min Act: -0.0005

Data Index: 112245 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0463. Min Act: -0.0005

Data Index: 751530 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0457. Min Act: -0.0005

Data Index: 1298978 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0432. Min Act: -0.0005

Data Index: 751202 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0455. Min Act: -0.0005

Data Index: 915692 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0480. Min Act: -0.0005

Data Index: 1186919 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0461. Min Act: -0.0005

Data Index: 268544 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0451. Min Act: -0.0005

Data Index: 513686 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0441. Min Act: -0.0005

Data Index: 634761 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0447. Min Act: -0.0005

Data Index: 457592 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0447. Min Act: -0.0005

Data Index: 126474 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0447. Min Act: -0.0005

Data Index: 692350 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0450. Min Act: -0.0005

Data Index: 299257 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0441. Min Act: -0.0005

Data Index: 273757 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0425. Min Act: -0.0005

Data Index: 1343769 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0435. Min Act: -0.0005

Data Index: 212344 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0440. Min Act: -0.0005

Data Index: 1049913 (C4 (Web Text))

Max Activating Token Index: 896