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

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

Neuron 902 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.7456. Min Act: -0.0000

Data Index: 1498836 (Python Code)

Max Activating Token Index: 853

Text #1

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.7664. Min Act: -0.0000

Data Index: 1513221 (Python Code)

Max Activating Token Index: 598

Text #2

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.5685. Min Act: -0.0000

Data Index: 1367049 (Python Code)

Max Activating Token Index: 758

Text #3

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.6470. Min Act: -0.0000

Data Index: 1553577 (Python Code)

Max Activating Token Index: 598

Text #4

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.5585. Min Act: -0.0000

Data Index: 1268769 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.5421. Min Act: -0.0000

Data Index: 1489804 (Python Code)

Max Activating Token Index: 720

Text #6

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.5111. Min Act: -0.0000

Data Index: 1485293 (Python Code)

Max Activating Token Index: 497

Text #7

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.4302. Min Act: -0.0000

Data Index: 484520 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.4245. Min Act: -0.0000

Data Index: 1624439 (Python Code)

Max Activating Token Index: 442

Text #9

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.4122. Min Act: -0.0000

Data Index: 140402 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.2768. Min Act: -0.0000

Data Index: 1467554 (Python Code)

Max Activating Token Index: 303

Text #11

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.2524. Min Act: -0.0000

Data Index: 1621274 (Python Code)

Max Activating Token Index: 134

Text #12

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.2580. Min Act: -0.0000

Data Index: 1548367 (Python Code)

Max Activating Token Index: 511

Text #13

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.3682. Min Act: -0.0000

Data Index: 1638583 (Python Code)

Max Activating Token Index: 600

Text #14

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.3392. Min Act: -0.0000

Data Index: 582686 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.4853. Min Act: -0.0000

Data Index: 1402313 (Python Code)

Max Activating Token Index: 916

Text #16

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.3481. Min Act: -0.0000

Data Index: 1519011 (Python Code)

Max Activating Token Index: 491

Text #17

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.2106. Min Act: -0.0000

Data Index: 1537990 (Python Code)

Max Activating Token Index: 1012

Text #18

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.3199. Min Act: -0.0000

Data Index: 1539609 (Python Code)

Max Activating Token Index: 609

Text #19

Max Range: 2.7664. Min Range: -2.7664

Max Act: 2.3126. Min Act: -0.0000

Data Index: 1413880 (Python Code)

Max Activating Token Index: 853