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

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

Neuron 3701 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7205. Min Range: -4.7205

Max Act: 4.7205. Min Act: -0.0000

Data Index: 1361942 (Python Code)

Max Activating Token Index: 713

Text #1

Max Range: 4.7205. Min Range: -4.7205

Max Act: 3.8728. Min Act: -0.0000

Data Index: 1636886 (Python Code)

Max Activating Token Index: 722

Text #2

Max Range: 4.7205. Min Range: -4.7205

Max Act: 3.6885. Min Act: -0.0000

Data Index: 1472196 (Python Code)

Max Activating Token Index: 548

Text #3

Max Range: 4.7205. Min Range: -4.7205

Max Act: 3.4302. Min Act: -0.0000

Data Index: 1445822 (Python Code)

Max Activating Token Index: 463

Text #4

Max Range: 4.7205. Min Range: -4.7205

Max Act: 2.9128. Min Act: -0.0000

Data Index: 1445318 (Python Code)

Max Activating Token Index: 849

Text #5

Max Range: 4.7205. Min Range: -4.7205

Max Act: 3.1480. Min Act: -0.0000

Data Index: 1471172 (Python Code)

Max Activating Token Index: 431

Text #6

Max Range: 4.7205. Min Range: -4.7205

Max Act: 3.2515. Min Act: -0.0000

Data Index: 1583108 (Python Code)

Max Activating Token Index: 747

Text #7

Max Range: 4.7205. Min Range: -4.7205

Max Act: 3.2608. Min Act: -0.0000

Data Index: 1627684 (Python Code)

Max Activating Token Index: 507

Text #8

Max Range: 4.7205. Min Range: -4.7205

Max Act: 3.1091. Min Act: -0.0000

Data Index: 1448569 (Python Code)

Max Activating Token Index: 512

Text #9

Max Range: 4.7205. Min Range: -4.7205

Max Act: 3.3739. Min Act: -0.0000

Data Index: 1629406 (Python Code)

Max Activating Token Index: 820

Text #10

Max Range: 4.7205. Min Range: -4.7205

Max Act: 3.1942. Min Act: -0.0000

Data Index: 1591068 (Python Code)

Max Activating Token Index: 617

Text #11

Max Range: 4.7205. Min Range: -4.7205

Max Act: 3.1711. Min Act: -0.0000

Data Index: 1502362 (Python Code)

Max Activating Token Index: 313

Text #12

Max Range: 4.7205. Min Range: -4.7205

Max Act: 3.0571. Min Act: -0.0000

Data Index: 1511074 (Python Code)

Max Activating Token Index: 647

Text #13

Max Range: 4.7205. Min Range: -4.7205

Max Act: 2.7571. Min Act: -0.0000

Data Index: 1585690 (Python Code)

Max Activating Token Index: 850

Text #14

Max Range: 4.7205. Min Range: -4.7205

Max Act: 3.0353. Min Act: -0.0000

Data Index: 1465029 (Python Code)

Max Activating Token Index: 989

Text #15

Max Range: 4.7205. Min Range: -4.7205

Max Act: 2.8444. Min Act: -0.0000

Data Index: 1420539 (Python Code)

Max Activating Token Index: 778

Text #16

Max Range: 4.7205. Min Range: -4.7205

Max Act: 2.9781. Min Act: -0.0000

Data Index: 1642591 (Python Code)

Max Activating Token Index: 114

Text #17

Max Range: 4.7205. Min Range: -4.7205

Max Act: 2.9692. Min Act: -0.0000

Data Index: 1513279 (Python Code)

Max Activating Token Index: 468

Text #18

Max Range: 4.7205. Min Range: -4.7205

Max Act: 2.9756. Min Act: -0.0000

Data Index: 1523713 (Python Code)

Max Activating Token Index: 611

Text #19

Max Range: 4.7205. Min Range: -4.7205

Max Act: 2.8180. Min Act: -0.0000

Data Index: 1608618 (Python Code)

Max Activating Token Index: 990