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

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

Neuron 626 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: 0.2857. Min Range: -0.2857

Max Act: 0.2857. Min Act: -0.0001

Data Index: 1135356 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2851. Min Act: -0.0001

Data Index: 591408 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2767. Min Act: -0.0001

Data Index: 1014083 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2601. Min Act: -0.0000

Data Index: 162452 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2771. Min Act: -0.0001

Data Index: 1034084 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2577. Min Act: -0.0000

Data Index: 299408 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2596. Min Act: -0.0000

Data Index: 1091115 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2490. Min Act: -0.0001

Data Index: 961386 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2658. Min Act: -0.0001

Data Index: 97650 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2579. Min Act: -0.0000

Data Index: 855437 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2562. Min Act: -0.0000

Data Index: 1058829 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1019073 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2416. Min Act: -0.0001

Data Index: 1154125 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2494. Min Act: -0.0001

Data Index: 913423 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2483. Min Act: -0.0001

Data Index: 59531 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2466. Min Act: -0.0000

Data Index: 1022969 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2377. Min Act: -0.0001

Data Index: 1259119 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2437. Min Act: -0.0000

Data Index: 578746 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2370. Min Act: -0.0000

Data Index: 458373 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2285. Min Act: -0.0000

Data Index: 486413 (C4 (Web Text))

Max Activating Token Index: 591