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

Dataset: The Pile

Neuron 3693 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: 13.1385. Min Range: -13.1385

Max Act: 13.0323. Min Act: -0.0000

Data Index: 1728889 (The Pile)

Max Activating Token Index: 1016

Text #1

Max Range: 13.1385. Min Range: -13.1385

Max Act: 12.8612. Min Act: -0.0000

Data Index: 591280 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 13.1385. Min Range: -13.1385

Max Act: 12.7715. Min Act: -0.0000

Data Index: 757283 (The Pile)

Max Activating Token Index: 880

Text #3

Max Range: 13.1385. Min Range: -13.1385

Max Act: 13.1385. Min Act: -0.0001

Data Index: 1829112 (The Pile)

Max Activating Token Index: 678

Text #4

Max Range: 13.1385. Min Range: -13.1385

Max Act: 13.0385. Min Act: -0.0001

Data Index: 1592580 (The Pile)

Max Activating Token Index: 512

Text #5

Max Range: 13.1385. Min Range: -13.1385

Max Act: 12.8464. Min Act: -0.0000

Data Index: 1379309 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 13.1385. Min Range: -13.1385

Max Act: 12.7210. Min Act: -0.0001

Data Index: 510755 (The Pile)

Max Activating Token Index: 542

Text #7

Max Range: 13.1385. Min Range: -13.1385

Max Act: 12.6182. Min Act: -0.0000

Data Index: 651958 (The Pile)

Max Activating Token Index: 841

Text #8

Max Range: 13.1385. Min Range: -13.1385

Max Act: 12.8883. Min Act: -0.0001

Data Index: 292248 (The Pile)

Max Activating Token Index: 437

Text #9

Max Range: 13.1385. Min Range: -13.1385

Max Act: 12.4607. Min Act: -0.0001

Data Index: 274044 (The Pile)

Max Activating Token Index: 323

Text #10

Max Range: 13.1385. Min Range: -13.1385

Max Act: 12.4480. Min Act: -0.0000

Data Index: 1376057 (The Pile)

Max Activating Token Index: 725

Text #11

Max Range: 13.1385. Min Range: -13.1385

Max Act: 11.9874. Min Act: -0.0000

Data Index: 1598187 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 13.1385. Min Range: -13.1385

Max Act: 12.4797. Min Act: -0.0001

Data Index: 1743753 (The Pile)

Max Activating Token Index: 468

Text #13

Max Range: 13.1385. Min Range: -13.1385

Max Act: 12.3735. Min Act: -0.0000

Data Index: 1348963 (The Pile)

Max Activating Token Index: 440

Text #14

Max Range: 13.1385. Min Range: -13.1385

Max Act: 12.2796. Min Act: -0.0000

Data Index: 1998841 (The Pile)

Max Activating Token Index: 667

Text #15

Max Range: 13.1385. Min Range: -13.1385

Max Act: 12.3571. Min Act: -0.0000

Data Index: 1079082 (The Pile)

Max Activating Token Index: 715

Text #16

Max Range: 13.1385. Min Range: -13.1385

Max Act: 12.3606. Min Act: -0.0001

Data Index: 329741 (The Pile)

Max Activating Token Index: 572

Text #17

Max Range: 13.1385. Min Range: -13.1385

Max Act: 12.0988. Min Act: -0.0000

Data Index: 123042 (The Pile)

Max Activating Token Index: 210

Text #18

Max Range: 13.1385. Min Range: -13.1385

Max Act: 12.5345. Min Act: -0.0000

Data Index: 135294 (The Pile)

Max Activating Token Index: 997

Text #19

Max Range: 13.1385. Min Range: -13.1385

Max Act: 12.3416. Min Act: -0.0001

Data Index: 945288 (The Pile)

Max Activating Token Index: 868