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

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

Neuron 2705 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: 0.9322. Min Range: -0.9322

Max Act: 0.9322. Min Act: -0.0001

Data Index: 1166478 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.9210. Min Act: -0.0001

Data Index: 838992 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.7659. Min Act: -0.0001

Data Index: 649904 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.7506. Min Act: -0.0001

Data Index: 67739 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.6803. Min Act: -0.0001

Data Index: 19520 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.7231. Min Act: -0.0001

Data Index: 754424 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.7168. Min Act: -0.0001

Data Index: 1215755 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.7170. Min Act: -0.0001

Data Index: 1080879 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.7274. Min Act: -0.0001

Data Index: 1328584 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.7751. Min Act: -0.0001

Data Index: 659856 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.6942. Min Act: -0.0001

Data Index: 803446 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.6841. Min Act: -0.0001

Data Index: 576661 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.6805. Min Act: -0.0001

Data Index: 835206 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.7429. Min Act: -0.0001

Data Index: 1326965 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.6780. Min Act: -0.0001

Data Index: 144784 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.6866. Min Act: -0.0001

Data Index: 873280 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.6546. Min Act: -0.0001

Data Index: 366020 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.6425. Min Act: -0.0001

Data Index: 295766 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.6573. Min Act: -0.0001

Data Index: 729763 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.6760. Min Act: -0.0001

Data Index: 89786 (C4 (Web Text))

Max Activating Token Index: 620