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

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

Neuron 3477 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.5975. Min Act: -0.0000

Data Index: 1548283 (Python Code)

Max Activating Token Index: 650

Text #1

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.5655. Min Act: -0.0000

Data Index: 1422208 (Python Code)

Max Activating Token Index: 647

Text #2

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.4943. Min Act: -0.0000

Data Index: 1575853 (Python Code)

Max Activating Token Index: 774

Text #3

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.3937. Min Act: -0.0000

Data Index: 1580854 (Python Code)

Max Activating Token Index: 310

Text #4

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.3561. Min Act: -0.0000

Data Index: 1509398 (Python Code)

Max Activating Token Index: 859

Text #5

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.4325. Min Act: -0.0000

Data Index: 1426847 (Python Code)

Max Activating Token Index: 394

Text #6

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.4409. Min Act: -0.0000

Data Index: 1400770 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.2716. Min Act: -0.0000

Data Index: 1436695 (Python Code)

Max Activating Token Index: 779

Text #8

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.2536. Min Act: -0.0000

Data Index: 1399268 (Python Code)

Max Activating Token Index: 297

Text #9

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.3681. Min Act: -0.0000

Data Index: 1586280 (Python Code)

Max Activating Token Index: 256

Text #10

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.2720. Min Act: -0.0000

Data Index: 1413525 (Python Code)

Max Activating Token Index: 242

Text #11

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.1813. Min Act: -0.0000

Data Index: 1514817 (Python Code)

Max Activating Token Index: 341

Text #12

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.0980. Min Act: -0.0000

Data Index: 1555233 (Python Code)

Max Activating Token Index: 138

Text #13

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.0649. Min Act: -0.0000

Data Index: 1595140 (Python Code)

Max Activating Token Index: 337

Text #14

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.0806. Min Act: -0.0000

Data Index: 1603623 (Python Code)

Max Activating Token Index: 319

Text #15

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.0462. Min Act: -0.0000

Data Index: 1481522 (Python Code)

Max Activating Token Index: 217

Text #16

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.0902. Min Act: -0.0000

Data Index: 1400947 (Python Code)

Max Activating Token Index: 485

Text #17

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.0973. Min Act: -0.0000

Data Index: 1598958 (Python Code)

Max Activating Token Index: 140

Text #18

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.0780. Min Act: -0.0000

Data Index: 1561093 (Python Code)

Max Activating Token Index: 343

Text #19

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.0450. Min Act: -0.0000

Data Index: 1600368 (Python Code)

Max Activating Token Index: 612