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

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

Neuron 3318 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4556. Min Act: -0.0000

Data Index: 1578295 (Python Code)

Max Activating Token Index: 417

Text #1

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1501151 (Python Code)

Max Activating Token Index: 400

Text #2

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1556536 (Python Code)

Max Activating Token Index: 518

Text #3

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4291. Min Act: -0.0000

Data Index: 58042 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4106. Min Act: -0.0000

Data Index: 1641442 (Python Code)

Max Activating Token Index: 333

Text #5

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1520546 (Python Code)

Max Activating Token Index: 995

Text #6

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1542479 (Python Code)

Max Activating Token Index: 360

Text #7

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1652128 (Python Code)

Max Activating Token Index: 938

Text #8

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4472. Min Act: -0.0000

Data Index: 461151 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3700. Min Act: -0.0000

Data Index: 1631399 (Python Code)

Max Activating Token Index: 346

Text #10

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3554. Min Act: -0.0000

Data Index: 1320307 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1424180 (Python Code)

Max Activating Token Index: 723

Text #12

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1380411 (Python Code)

Max Activating Token Index: 962

Text #13

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3706. Min Act: -0.0000

Data Index: 1476949 (Python Code)

Max Activating Token Index: 771

Text #14

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3864. Min Act: -0.0000

Data Index: 1271529 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1392523 (Python Code)

Max Activating Token Index: 587

Text #16

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3501. Min Act: -0.0000

Data Index: 1389383 (Python Code)

Max Activating Token Index: 948

Text #17

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3777. Min Act: -0.0000

Data Index: 1101705 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1447771 (Python Code)

Max Activating Token Index: 224

Text #19

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4048. Min Act: -0.0000

Data Index: 1359969 (Python Code)

Max Activating Token Index: 298