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

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

Neuron 4328 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.2020. Min Act: -0.0000

Data Index: 57101 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1881. Min Act: -0.0000

Data Index: 443355 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1189461 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1932. Min Act: -0.0000

Data Index: 487486 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1312718 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1697. Min Act: -0.0000

Data Index: 158248 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1743. Min Act: -0.0000

Data Index: 115651 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1723. Min Act: -0.0000

Data Index: 1653372 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1532438 (Python Code)

Max Activating Token Index: 993

Text #9

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1661. Min Act: -0.0000

Data Index: 1496671 (Python Code)

Max Activating Token Index: 16

Text #10

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1545. Min Act: -0.0000

Data Index: 755433 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1698. Min Act: -0.0000

Data Index: 1148089 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1534. Min Act: -0.0000

Data Index: 1560534 (Python Code)

Max Activating Token Index: 490

Text #13

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1296. Min Act: -0.0000

Data Index: 250577 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1557. Min Act: -0.0000

Data Index: 1248957 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1494. Min Act: -0.0000

Data Index: 797720 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1352. Min Act: -0.0000

Data Index: 26261 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1517. Min Act: -0.0000

Data Index: 657354 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1522. Min Act: -0.0000

Data Index: 583952 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 0.2020. Min Range: -0.2020

Max Act: 0.1408. Min Act: -0.0000

Data Index: 659925 (C4 (Web Text))

Max Activating Token Index: 981