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

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

Neuron 3801 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0833. Min Act: -0.0000

Data Index: 1540476 (Python Code)

Max Activating Token Index: 206

Text #1

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0940. Min Act: -0.0001

Data Index: 1617274 (Python Code)

Max Activating Token Index: 776

Text #2

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0775. Min Act: -0.0000

Data Index: 1471448 (Python Code)

Max Activating Token Index: 571

Text #3

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0726. Min Act: -0.0000

Data Index: 1414115 (Python Code)

Max Activating Token Index: 195

Text #4

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0659. Min Act: -0.0000

Data Index: 1503547 (Python Code)

Max Activating Token Index: 489

Text #5

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0628. Min Act: -0.0000

Data Index: 1591118 (Python Code)

Max Activating Token Index: 262

Text #6

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0595. Min Act: -0.0000

Data Index: 101098 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1565672 (Python Code)

Max Activating Token Index: 211

Text #8

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1610679 (Python Code)

Max Activating Token Index: 67

Text #9

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0574. Min Act: -0.0000

Data Index: 1488549 (Python Code)

Max Activating Token Index: 106

Text #10

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0529. Min Act: -0.0000

Data Index: 1384207 (Python Code)

Max Activating Token Index: 88

Text #11

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0579. Min Act: -0.0000

Data Index: 1433874 (Python Code)

Max Activating Token Index: 241

Text #12

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1533815 (Python Code)

Max Activating Token Index: 557

Text #13

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0485. Min Act: -0.0000

Data Index: 1644393 (Python Code)

Max Activating Token Index: 278

Text #14

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0534. Min Act: -0.0000

Data Index: 1409611 (Python Code)

Max Activating Token Index: 506

Text #15

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0556. Min Act: -0.0000

Data Index: 1400098 (Python Code)

Max Activating Token Index: 343

Text #16

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0530. Min Act: -0.0000

Data Index: 1613931 (Python Code)

Max Activating Token Index: 81

Text #17

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1208409 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0559. Min Act: -0.0001

Data Index: 772 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0495. Min Act: -0.0000

Data Index: 572234 (C4 (Web Text))

Max Activating Token Index: 162