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

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

Neuron 3498 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.3549. Min Act: -0.0001

Data Index: 813788 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.3180. Min Act: -0.0000

Data Index: 1248417 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.3176. Min Act: -0.0001

Data Index: 1435834 (Python Code)

Max Activating Token Index: 670

Text #3

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.3184. Min Act: -0.0001

Data Index: 1526400 (Python Code)

Max Activating Token Index: 115

Text #4

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.3138. Min Act: -0.0001

Data Index: 1490143 (Python Code)

Max Activating Token Index: 637

Text #5

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.3090. Min Act: -0.0001

Data Index: 184047 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2773. Min Act: -0.0001

Data Index: 1333218 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2715. Min Act: -0.0001

Data Index: 1359769 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2789. Min Act: -0.0001

Data Index: 1546529 (Python Code)

Max Activating Token Index: 174

Text #9

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2996. Min Act: -0.0001

Data Index: 1548628 (Python Code)

Max Activating Token Index: 922

Text #10

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2732. Min Act: -0.0001

Data Index: 19991 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2647. Min Act: -0.0001

Data Index: 288465 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2542. Min Act: -0.0001

Data Index: 242723 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2613. Min Act: -0.0000

Data Index: 246468 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2533. Min Act: -0.0001

Data Index: 1578071 (Python Code)

Max Activating Token Index: 747

Text #15

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2413. Min Act: -0.0001

Data Index: 1581361 (Python Code)

Max Activating Token Index: 89

Text #16

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2403. Min Act: -0.0001

Data Index: 404582 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2410. Min Act: -0.0001

Data Index: 1535168 (Python Code)

Max Activating Token Index: 256

Text #18

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2458. Min Act: -0.0001

Data Index: 613945 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2437. Min Act: -0.0001

Data Index: 264357 (C4 (Web Text))

Max Activating Token Index: 406