Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2196 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0001

Data Index: 1618350 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1455366 (Python Code)

Max Activating Token Index: 522

Text #2

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1373661 (Python Code)

Max Activating Token Index: 369

Text #3

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0667. Min Act: -0.0001

Data Index: 1496498 (Python Code)

Max Activating Token Index: 618

Text #4

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1629689 (Python Code)

Max Activating Token Index: 108

Text #5

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0492. Min Act: -0.0001

Data Index: 1555574 (Python Code)

Max Activating Token Index: 830

Text #6

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0464. Min Act: -0.0001

Data Index: 807554 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0431. Min Act: -0.0001

Data Index: 631309 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1509689 (Python Code)

Max Activating Token Index: 577

Text #9

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0483. Min Act: -0.0001

Data Index: 457102 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0480. Min Act: -0.0001

Data Index: 1542548 (Python Code)

Max Activating Token Index: 100

Text #11

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1553606 (Python Code)

Max Activating Token Index: 119

Text #12

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0480. Min Act: -0.0001

Data Index: 206156 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0460. Min Act: -0.0001

Data Index: 438948 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0431. Min Act: -0.0001

Data Index: 883496 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0447. Min Act: -0.0001

Data Index: 1454637 (Python Code)

Max Activating Token Index: 422

Text #16

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1447556 (Python Code)

Max Activating Token Index: 162

Text #17

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0452. Min Act: -0.0001

Data Index: 1629604 (Python Code)

Max Activating Token Index: 752

Text #18

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0472. Min Act: -0.0001

Data Index: 1542803 (Python Code)

Max Activating Token Index: 111

Text #19

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0471. Min Act: -0.0001

Data Index: 1495417 (Python Code)

Max Activating Token Index: 336