Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1759 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0876. Min Act: -0.0000

Data Index: 79774 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1639624 (Python Code)

Max Activating Token Index: 629

Text #2

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0629. Min Act: -0.0000

Data Index: 1397008 (Python Code)

Max Activating Token Index: 53

Text #3

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1589071 (Python Code)

Max Activating Token Index: 211

Text #4

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0599. Min Act: -0.0000

Data Index: 1174255 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1498451 (Python Code)

Max Activating Token Index: 858

Text #6

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0495. Min Act: -0.0001

Data Index: 1415565 (Python Code)

Max Activating Token Index: 200

Text #7

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0531. Min Act: -0.0001

Data Index: 1419335 (Python Code)

Max Activating Token Index: 268

Text #8

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0481. Min Act: -0.0001

Data Index: 1525287 (Python Code)

Max Activating Token Index: 99

Text #9

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0534. Min Act: -0.0001

Data Index: 65166 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0420. Min Act: -0.0000

Data Index: 965219 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0430. Min Act: -0.0000

Data Index: 1110893 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0400. Min Act: -0.0000

Data Index: 1096042 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0438. Min Act: -0.0000

Data Index: 193110 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0419. Min Act: -0.0000

Data Index: 1578166 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0398. Min Act: -0.0000

Data Index: 756420 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0410. Min Act: -0.0001

Data Index: 1609527 (Python Code)

Max Activating Token Index: 389

Text #17

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0451. Min Act: -0.0000

Data Index: 1229280 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0416. Min Act: -0.0000

Data Index: 1573338 (Python Code)

Max Activating Token Index: 134

Text #19

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0355. Min Act: -0.0000

Data Index: 52112 (C4 (Web Text))

Max Activating Token Index: 178