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

Dataset: The Pile

Neuron 1998 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.3243. Min Act: -0.0000

Data Index: 652008 (The Pile)

Max Activating Token Index: 127

Text #1

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1352948 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.3471. Min Act: -0.0000

Data Index: 1178013 (The Pile)

Max Activating Token Index: 141

Text #3

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2910. Min Act: -0.0000

Data Index: 1311412 (The Pile)

Max Activating Token Index: 89

Text #4

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2693. Min Act: -0.0000

Data Index: 593549 (The Pile)

Max Activating Token Index: 347

Text #5

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1052262 (The Pile)

Max Activating Token Index: 169

Text #6

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1468700 (The Pile)

Max Activating Token Index: 293

Text #7

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1055778 (The Pile)

Max Activating Token Index: 60

Text #8

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1672272 (The Pile)

Max Activating Token Index: 507

Text #9

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1954600 (The Pile)

Max Activating Token Index: 945

Text #10

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1097132 (The Pile)

Max Activating Token Index: 100

Text #11

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2650. Min Act: -0.0000

Data Index: 383153 (The Pile)

Max Activating Token Index: 175

Text #12

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2678. Min Act: -0.0000

Data Index: 1169978 (The Pile)

Max Activating Token Index: 179

Text #13

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2415. Min Act: -0.0000

Data Index: 993005 (The Pile)

Max Activating Token Index: 704

Text #14

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2561. Min Act: -0.0000

Data Index: 1576152 (The Pile)

Max Activating Token Index: 877

Text #15

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1902532 (The Pile)

Max Activating Token Index: 862

Text #16

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2659. Min Act: -0.0000

Data Index: 181989 (The Pile)

Max Activating Token Index: 385

Text #17

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1746397 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1570581 (The Pile)

Max Activating Token Index: 944

Text #19

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2632. Min Act: -0.0000

Data Index: 66430 (The Pile)

Max Activating Token Index: 310