Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1366 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0434. Min Range: -1.0434

Max Act: 1.0243. Min Act: -0.0001

Data Index: 1070079 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 1.0434. Min Range: -1.0434

Max Act: 1.0434. Min Act: -0.0001

Data Index: 1148097 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9688. Min Act: -0.0001

Data Index: 577584 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9561. Min Act: -0.0001

Data Index: 456146 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9913. Min Act: -0.0001

Data Index: 1113421 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9358. Min Act: -0.0001

Data Index: 177486 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9017. Min Act: -0.0001

Data Index: 556663 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9066. Min Act: -0.0001

Data Index: 509609 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8698. Min Act: -0.0001

Data Index: 424350 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8952. Min Act: -0.0001

Data Index: 92743 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8290. Min Act: -0.0001

Data Index: 11274 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8252. Min Act: -0.0001

Data Index: 106886 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9162. Min Act: -0.0001

Data Index: 480331 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8183. Min Act: -0.0001

Data Index: 195105 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8750. Min Act: -0.0001

Data Index: 1333855 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8764. Min Act: -0.0001

Data Index: 712200 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.7745. Min Act: -0.0001

Data Index: 1013607 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8643. Min Act: -0.0001

Data Index: 1275993 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8331. Min Act: -0.0001

Data Index: 896432 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8094. Min Act: -0.0001

Data Index: 317017 (C4 (Web Text))

Max Activating Token Index: 430