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

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

Neuron 5123 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.1766. Min Act: 0.0001

Data Index: 1288804 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.0942. Min Act: 0.0000

Data Index: 1007418 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.0714. Min Act: -0.0000

Data Index: 8521 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.0031. Min Act: 0.0001

Data Index: 738555 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.9646. Min Act: 0.0000

Data Index: 462882 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.9364. Min Act: 0.0000

Data Index: 847552 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.9259. Min Act: -0.0000

Data Index: 731732 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.9270. Min Act: -0.0000

Data Index: 1174325 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8325. Min Act: 0.0002

Data Index: 482235 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1265633 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8804. Min Act: 0.0000

Data Index: 83402 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8479. Min Act: -0.0000

Data Index: 220487 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8278. Min Act: -0.0000

Data Index: 636174 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8122. Min Act: -0.0000

Data Index: 598596 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8443. Min Act: -0.0000

Data Index: 980129 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.7355. Min Act: -0.0000

Data Index: 966548 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.7735. Min Act: -0.0000

Data Index: 618634 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.7738. Min Act: -0.0000

Data Index: 622247 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.7743. Min Act: -0.0000

Data Index: 1064417 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1159119 (C4 (Web Text))

Max Activating Token Index: 883