Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3787 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.7904. Min Act: -0.0001

Data Index: 659268 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.6712. Min Act: -0.0001

Data Index: 147217 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.6203. Min Act: -0.0001

Data Index: 870441 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.5548. Min Act: -0.0001

Data Index: 54757 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.3621. Min Act: -0.0001

Data Index: 1001544 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.1084. Min Act: -0.0001

Data Index: 152111 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 1.7904. Min Range: -1.7904

Max Act: 0.9794. Min Act: -0.0001

Data Index: 299596 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.1751. Min Act: -0.0001

Data Index: 67925 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.1234. Min Act: -0.0001

Data Index: 243811 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.0952. Min Act: -0.0001

Data Index: 1345805 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.0359. Min Act: -0.0001

Data Index: 394436 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.1247. Min Act: -0.0001

Data Index: 399018 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 1.7904. Min Range: -1.7904

Max Act: 0.9930. Min Act: -0.0001

Data Index: 713520 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 1.7904. Min Range: -1.7904

Max Act: 1.0026. Min Act: -0.0001

Data Index: 318915 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 1.7904. Min Range: -1.7904

Max Act: 0.9976. Min Act: -0.0001

Data Index: 1266352 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 1.7904. Min Range: -1.7904

Max Act: 0.9434. Min Act: -0.0001

Data Index: 1301362 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 1.7904. Min Range: -1.7904

Max Act: 0.9381. Min Act: -0.0001

Data Index: 224020 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 1.7904. Min Range: -1.7904

Max Act: 0.9661. Min Act: -0.0001

Data Index: 517127 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 1.7904. Min Range: -1.7904

Max Act: 0.8856. Min Act: -0.0001

Data Index: 1113987 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 1.7904. Min Range: -1.7904

Max Act: 0.9778. Min Act: -0.0001

Data Index: 435779 (C4 (Web Text))

Max Activating Token Index: 951