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

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

Neuron 1307 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1702. Min Range: -3.1702

Max Act: 2.9135. Min Act: -0.0000

Data Index: 1044289 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 3.1702. Min Range: -3.1702

Max Act: 3.1493. Min Act: -0.0000

Data Index: 201935 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 3.1702. Min Range: -3.1702

Max Act: 3.1702. Min Act: -0.0000

Data Index: 514837 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 3.1702. Min Range: -3.1702

Max Act: 2.9345. Min Act: -0.0000

Data Index: 1334561 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 3.1702. Min Range: -3.1702

Max Act: 2.6531. Min Act: -0.0000

Data Index: 1148715 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 3.1702. Min Range: -3.1702

Max Act: 2.7368. Min Act: -0.0000

Data Index: 744659 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 3.1702. Min Range: -3.1702

Max Act: 2.5778. Min Act: -0.0000

Data Index: 777990 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 3.1702. Min Range: -3.1702

Max Act: 2.5231. Min Act: -0.0000

Data Index: 934978 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 3.1702. Min Range: -3.1702

Max Act: 2.3885. Min Act: -0.0000

Data Index: 254560 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 3.1702. Min Range: -3.1702

Max Act: 2.2299. Min Act: -0.0000

Data Index: 1373476 (Python Code)

Max Activating Token Index: 583

Text #10

Max Range: 3.1702. Min Range: -3.1702

Max Act: 2.3270. Min Act: -0.0000

Data Index: 660427 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 3.1702. Min Range: -3.1702

Max Act: 2.4197. Min Act: -0.0000

Data Index: 1064188 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 3.1702. Min Range: -3.1702

Max Act: 2.3053. Min Act: -0.0000

Data Index: 89438 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 3.1702. Min Range: -3.1702

Max Act: 2.2697. Min Act: -0.0000

Data Index: 1071153 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 3.1702. Min Range: -3.1702

Max Act: 2.1476. Min Act: -0.0000

Data Index: 490163 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 3.1702. Min Range: -3.1702

Max Act: 2.2436. Min Act: -0.0000

Data Index: 1125269 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 3.1702. Min Range: -3.1702

Max Act: 2.0652. Min Act: -0.0000

Data Index: 1128748 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 3.1702. Min Range: -3.1702

Max Act: 2.1848. Min Act: -0.0000

Data Index: 5531 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 3.1702. Min Range: -3.1702

Max Act: 2.1527. Min Act: -0.0000

Data Index: 409679 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 3.1702. Min Range: -3.1702

Max Act: 2.1350. Min Act: -0.0000

Data Index: 80913 (C4 (Web Text))

Max Activating Token Index: 125