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

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

Neuron 526 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: 1.5493. Min Range: -1.5493

Max Act: 1.5060. Min Act: -0.0000

Data Index: 350920 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.5493. Min Act: -0.0000

Data Index: 1444840 (Python Code)

Max Activating Token Index: 73

Text #2

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.3916. Min Act: -0.0000

Data Index: 1317729 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.2590. Min Act: -0.0000

Data Index: 956079 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.3615. Min Act: -0.0001

Data Index: 97892 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.2767. Min Act: -0.0000

Data Index: 1638049 (Python Code)

Max Activating Token Index: 650

Text #6

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.3895. Min Act: -0.0000

Data Index: 195870 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.2965. Min Act: -0.0000

Data Index: 1638699 (Python Code)

Max Activating Token Index: 494

Text #8

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.3014. Min Act: -0.0000

Data Index: 1078994 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.2479. Min Act: -0.0000

Data Index: 299379 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.2347. Min Act: -0.0000

Data Index: 836096 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.2778. Min Act: -0.0000

Data Index: 1586427 (Python Code)

Max Activating Token Index: 828

Text #12

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.2801. Min Act: -0.0000

Data Index: 1302882 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.2494. Min Act: -0.0000

Data Index: 1452854 (Python Code)

Max Activating Token Index: 562

Text #14

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.2451. Min Act: -0.0000

Data Index: 1403448 (Python Code)

Max Activating Token Index: 475

Text #15

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.2028. Min Act: -0.0000

Data Index: 645332 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.2628. Min Act: -0.0000

Data Index: 1013888 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.1345. Min Act: -0.0000

Data Index: 1409120 (Python Code)

Max Activating Token Index: 461

Text #18

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.2612. Min Act: -0.0000

Data Index: 1639948 (Python Code)

Max Activating Token Index: 426

Text #19

Max Range: 1.5493. Min Range: -1.5493

Max Act: 1.2381. Min Act: -0.0000

Data Index: 1402782 (Python Code)

Max Activating Token Index: 180