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

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

Neuron 4821 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2714. Min Range: -1.2714

Max Act: 1.2714. Min Act: -0.0000

Data Index: 153260 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 1.2714. Min Range: -1.2714

Max Act: 1.1450. Min Act: -0.0000

Data Index: 1155730 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 1.2714. Min Range: -1.2714

Max Act: 1.0912. Min Act: -0.0000

Data Index: 663233 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 1.2714. Min Range: -1.2714

Max Act: 1.1423. Min Act: -0.0000

Data Index: 87637 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 1.2714. Min Range: -1.2714

Max Act: 1.0317. Min Act: -0.0000

Data Index: 890412 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 1.2714. Min Range: -1.2714

Max Act: 1.1073. Min Act: -0.0000

Data Index: 774096 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 1.2714. Min Range: -1.2714

Max Act: 1.0260. Min Act: -0.0000

Data Index: 376656 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 1.2714. Min Range: -1.2714

Max Act: 1.0466. Min Act: -0.0000

Data Index: 629181 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.9582. Min Act: -0.0000

Data Index: 59667 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1243789 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.8065. Min Act: -0.0001

Data Index: 276841 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 1.2714. Min Range: -1.2714

Max Act: 1.0297. Min Act: -0.0001

Data Index: 550500 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.9703. Min Act: -0.0000

Data Index: 717735 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.8891. Min Act: -0.0000

Data Index: 174936 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.9831. Min Act: -0.0000

Data Index: 364825 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.8884. Min Act: -0.0001

Data Index: 1021594 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.9338. Min Act: -0.0000

Data Index: 579459 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.9736. Min Act: -0.0001

Data Index: 600960 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.9259. Min Act: -0.0000

Data Index: 1282465 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.8271. Min Act: -0.0001

Data Index: 1117205 (C4 (Web Text))

Max Activating Token Index: 671