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

Dataset: The Pile

Neuron 2470 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1438132 (The Pile)

Max Activating Token Index: 387

Text #1

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6538. Min Act: -0.0000

Data Index: 878511 (The Pile)

Max Activating Token Index: 957

Text #2

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5418. Min Act: -0.0000

Data Index: 357052 (The Pile)

Max Activating Token Index: 35

Text #3

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1975846 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1903112 (The Pile)

Max Activating Token Index: 632

Text #5

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6549. Min Act: -0.0000

Data Index: 382707 (The Pile)

Max Activating Token Index: 738

Text #6

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6169. Min Act: -0.0000

Data Index: 1160063 (The Pile)

Max Activating Token Index: 39

Text #7

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6432. Min Act: -0.0000

Data Index: 258518 (The Pile)

Max Activating Token Index: 842

Text #8

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5608. Min Act: -0.0000

Data Index: 1121304 (The Pile)

Max Activating Token Index: 797

Text #9

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6028. Min Act: -0.0000

Data Index: 914004 (The Pile)

Max Activating Token Index: 593

Text #10

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5533. Min Act: -0.0000

Data Index: 359178 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4679. Min Act: -0.0000

Data Index: 615132 (The Pile)

Max Activating Token Index: 663

Text #12

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1180472 (The Pile)

Max Activating Token Index: 39

Text #13

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1655483 (The Pile)

Max Activating Token Index: 34

Text #14

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5319. Min Act: -0.0000

Data Index: 1080211 (The Pile)

Max Activating Token Index: 63

Text #15

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4724. Min Act: -0.0000

Data Index: 1434415 (The Pile)

Max Activating Token Index: 708

Text #16

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5372. Min Act: -0.0000

Data Index: 1641182 (The Pile)

Max Activating Token Index: 870

Text #17

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1281332 (The Pile)

Max Activating Token Index: 921

Text #18

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4417. Min Act: -0.0000

Data Index: 1976600 (The Pile)

Max Activating Token Index: 921

Text #19

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4463. Min Act: -0.0000

Data Index: 352730 (The Pile)

Max Activating Token Index: 824