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

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

Neuron 4406 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.6487. Min Act: -0.0000

Data Index: 212052 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5697. Min Act: -0.0000

Data Index: 159212 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5406. Min Act: -0.0000

Data Index: 1023105 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5563. Min Act: -0.0000

Data Index: 817700 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1239848 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5527. Min Act: -0.0000

Data Index: 271988 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1138208 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5516. Min Act: -0.0000

Data Index: 571961 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5055. Min Act: -0.0000

Data Index: 809541 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1073965 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5481. Min Act: -0.0000

Data Index: 390498 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1276586 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5244. Min Act: -0.0000

Data Index: 816811 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5127. Min Act: -0.0000

Data Index: 408437 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5301. Min Act: -0.0000

Data Index: 724555 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4961. Min Act: -0.0000

Data Index: 457982 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4510. Min Act: -0.0000

Data Index: 782990 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1356878 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5032. Min Act: -0.0000

Data Index: 901990 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4844. Min Act: -0.0000

Data Index: 1100120 (C4 (Web Text))

Max Activating Token Index: 321