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

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

Neuron 472 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.7510. Min Act: -0.0000

Data Index: 191132 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6330. Min Act: -0.0000

Data Index: 366995 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5618. Min Act: -0.0000

Data Index: 695358 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5660. Min Act: -0.0000

Data Index: 1079611 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5232. Min Act: -0.0000

Data Index: 86886 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5390. Min Act: -0.0000

Data Index: 959586 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5028. Min Act: -0.0001

Data Index: 895633 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5266. Min Act: 0.0000

Data Index: 1261784 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5240. Min Act: -0.0000

Data Index: 178329 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4970. Min Act: -0.0000

Data Index: 420662 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4928. Min Act: -0.0000

Data Index: 89432 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4904. Min Act: -0.0000

Data Index: 425394 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4695. Min Act: -0.0000

Data Index: 49138 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4984. Min Act: -0.0000

Data Index: 826500 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1095234 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4725. Min Act: -0.0000

Data Index: 1328028 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4705. Min Act: -0.0000

Data Index: 985286 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4558. Min Act: -0.0000

Data Index: 94685 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4341. Min Act: -0.0000

Data Index: 111014 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4610. Min Act: -0.0000

Data Index: 174096 (C4 (Web Text))

Max Activating Token Index: 237