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

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

Neuron 701 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: 1.5472. Min Range: -1.5472

Max Act: 1.5472. Min Act: -0.0001

Data Index: 1523087 (Python Code)

Max Activating Token Index: 383

Text #1

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.5005. Min Act: -0.0001

Data Index: 1524556 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.5005. Min Act: -0.0001

Data Index: 1592439 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.4420. Min Act: -0.0001

Data Index: 1503186 (Python Code)

Max Activating Token Index: 790

Text #4

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1541833 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.4153. Min Act: -0.0001

Data Index: 1368325 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1459888 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.4153. Min Act: -0.0001

Data Index: 1362377 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1482847 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.4153. Min Act: -0.0001

Data Index: 1575726 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1647418 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.4153. Min Act: -0.0001

Data Index: 1655847 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.4667. Min Act: -0.0000

Data Index: 1612774 (Python Code)

Max Activating Token Index: 476

Text #13

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3302. Min Act: -0.0000

Data Index: 1656085 (Python Code)

Max Activating Token Index: 258

Text #14

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3590. Min Act: -0.0001

Data Index: 1597926 (Python Code)

Max Activating Token Index: 448

Text #15

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.4226. Min Act: -0.0000

Data Index: 1571317 (Python Code)

Max Activating Token Index: 735

Text #16

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.2545. Min Act: -0.0000

Data Index: 1580929 (Python Code)

Max Activating Token Index: 867

Text #17

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.2650. Min Act: -0.0001

Data Index: 1419065 (Python Code)

Max Activating Token Index: 424

Text #18

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.2521. Min Act: -0.0000

Data Index: 1427311 (Python Code)

Max Activating Token Index: 269

Text #19

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3663. Min Act: -0.0001

Data Index: 1508878 (Python Code)

Max Activating Token Index: 64