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

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

Neuron 5825 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.4321. Min Act: -0.0000

Data Index: 1580354 (Python Code)

Max Activating Token Index: 156

Text #1

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.1579. Min Act: -0.0000

Data Index: 1410049 (Python Code)

Max Activating Token Index: 128

Text #2

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.0756. Min Act: -0.0000

Data Index: 1548051 (Python Code)

Max Activating Token Index: 730

Text #3

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.2369. Min Act: -0.0000

Data Index: 1501046 (Python Code)

Max Activating Token Index: 44

Text #4

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.3428. Min Act: -0.0000

Data Index: 1637950 (Python Code)

Max Activating Token Index: 25

Text #5

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.1624. Min Act: -0.0000

Data Index: 1567682 (Python Code)

Max Activating Token Index: 642

Text #6

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.2958. Min Act: -0.0000

Data Index: 1531855 (Python Code)

Max Activating Token Index: 380

Text #7

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.0626. Min Act: -0.0000

Data Index: 1647713 (Python Code)

Max Activating Token Index: 8

Text #8

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.1977. Min Act: -0.0000

Data Index: 1607381 (Python Code)

Max Activating Token Index: 211

Text #9

Max Range: 3.4321. Min Range: -3.4321

Max Act: 2.8326. Min Act: -0.0000

Data Index: 1482594 (Python Code)

Max Activating Token Index: 213

Text #10

Max Range: 3.4321. Min Range: -3.4321

Max Act: 2.8307. Min Act: -0.0000

Data Index: 1586033 (Python Code)

Max Activating Token Index: 98

Text #11

Max Range: 3.4321. Min Range: -3.4321

Max Act: 2.9728. Min Act: -0.0000

Data Index: 1645556 (Python Code)

Max Activating Token Index: 355

Text #12

Max Range: 3.4321. Min Range: -3.4321

Max Act: 2.8208. Min Act: -0.0000

Data Index: 1514920 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.1073. Min Act: -0.0000

Data Index: 1422275 (Python Code)

Max Activating Token Index: 671

Text #14

Max Range: 3.4321. Min Range: -3.4321

Max Act: 2.7660. Min Act: -0.0000

Data Index: 1650665 (Python Code)

Max Activating Token Index: 241

Text #15

Max Range: 3.4321. Min Range: -3.4321

Max Act: 2.8751. Min Act: -0.0000

Data Index: 1394625 (Python Code)

Max Activating Token Index: 931

Text #16

Max Range: 3.4321. Min Range: -3.4321

Max Act: 2.7455. Min Act: -0.0000

Data Index: 1407649 (Python Code)

Max Activating Token Index: 684

Text #17

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.0297. Min Act: -0.0000

Data Index: 1495389 (Python Code)

Max Activating Token Index: 737

Text #18

Max Range: 3.4321. Min Range: -3.4321

Max Act: 2.8773. Min Act: -0.0000

Data Index: 1610526 (Python Code)

Max Activating Token Index: 301

Text #19

Max Range: 3.4321. Min Range: -3.4321

Max Act: 2.8790. Min Act: -0.0000

Data Index: 1444623 (Python Code)

Max Activating Token Index: 20