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

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

Neuron 2101 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4455. Min Range: -4.4455

Max Act: 4.2830. Min Act: -0.0000

Data Index: 925794 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 4.4455. Min Range: -4.4455

Max Act: 4.4455. Min Act: -0.0000

Data Index: 856462 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 4.4455. Min Range: -4.4455

Max Act: 4.3982. Min Act: -0.0000

Data Index: 599110 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 4.4455. Min Range: -4.4455

Max Act: 4.3432. Min Act: -0.0000

Data Index: 291495 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 4.4455. Min Range: -4.4455

Max Act: 4.2942. Min Act: -0.0000

Data Index: 1134692 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 4.4455. Min Range: -4.4455

Max Act: 4.1025. Min Act: -0.0000

Data Index: 213096 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 4.4455. Min Range: -4.4455

Max Act: 4.0833. Min Act: -0.0000

Data Index: 1055592 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 4.4455. Min Range: -4.4455

Max Act: 4.2155. Min Act: -0.0000

Data Index: 828978 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 4.4455. Min Range: -4.4455

Max Act: 3.8224. Min Act: -0.0000

Data Index: 577464 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 4.4455. Min Range: -4.4455

Max Act: 4.1105. Min Act: -0.0000

Data Index: 712802 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 4.4455. Min Range: -4.4455

Max Act: 3.8799. Min Act: -0.0000

Data Index: 1327325 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 4.4455. Min Range: -4.4455

Max Act: 3.6862. Min Act: -0.0000

Data Index: 629040 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 4.4455. Min Range: -4.4455

Max Act: 3.7663. Min Act: -0.0000

Data Index: 74845 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 4.4455. Min Range: -4.4455

Max Act: 3.7327. Min Act: -0.0000

Data Index: 242283 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 4.4455. Min Range: -4.4455

Max Act: 3.5210. Min Act: -0.0000

Data Index: 738775 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 4.4455. Min Range: -4.4455

Max Act: 3.3224. Min Act: -0.0000

Data Index: 642038 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 4.4455. Min Range: -4.4455

Max Act: 3.6418. Min Act: -0.0000

Data Index: 547903 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 4.4455. Min Range: -4.4455

Max Act: 3.9702. Min Act: -0.0000

Data Index: 415914 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 4.4455. Min Range: -4.4455

Max Act: 3.4507. Min Act: -0.0000

Data Index: 143253 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 4.4455. Min Range: -4.4455

Max Act: 3.3933. Min Act: -0.0000

Data Index: 366599 (C4 (Web Text))

Max Activating Token Index: 342