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

Dataset: The Pile

Neuron 2611 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.6865. Min Act: -0.0000

Data Index: 959745 (The Pile)

Max Activating Token Index: 625

Text #1

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.4701. Min Act: -0.0000

Data Index: 151754 (The Pile)

Max Activating Token Index: 627

Text #2

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.7489. Min Act: -0.0000

Data Index: 194228 (The Pile)

Max Activating Token Index: 31

Text #3

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.1944. Min Act: -0.0000

Data Index: 1382539 (The Pile)

Max Activating Token Index: 638

Text #4

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.1845. Min Act: -0.0000

Data Index: 1360421 (The Pile)

Max Activating Token Index: 787

Text #5

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.5169. Min Act: -0.0000

Data Index: 1290620 (The Pile)

Max Activating Token Index: 71

Text #6

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.7048. Min Act: -0.0000

Data Index: 1986919 (The Pile)

Max Activating Token Index: 594

Text #7

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.4892. Min Act: -0.0000

Data Index: 1489773 (The Pile)

Max Activating Token Index: 590

Text #8

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.6593. Min Act: -0.0000

Data Index: 1777901 (The Pile)

Max Activating Token Index: 652

Text #9

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.4740. Min Act: -0.0000

Data Index: 1185391 (The Pile)

Max Activating Token Index: 503

Text #10

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.5690. Min Act: -0.0000

Data Index: 1652817 (The Pile)

Max Activating Token Index: 507

Text #11

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.2023. Min Act: -0.0000

Data Index: 578138 (The Pile)

Max Activating Token Index: 636

Text #12

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.3465. Min Act: -0.0000

Data Index: 1856378 (The Pile)

Max Activating Token Index: 266

Text #13

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.1420. Min Act: -0.0000

Data Index: 1932748 (The Pile)

Max Activating Token Index: 793

Text #14

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.5065. Min Act: -0.0000

Data Index: 983133 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.4430. Min Act: -0.0000

Data Index: 27847 (The Pile)

Max Activating Token Index: 965

Text #16

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.0564. Min Act: -0.0000

Data Index: 616265 (The Pile)

Max Activating Token Index: 748

Text #17

Max Range: 5.7489. Min Range: -5.7489

Max Act: 4.9998. Min Act: -0.0000

Data Index: 553762 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.3844. Min Act: -0.0000

Data Index: 322730 (The Pile)

Max Activating Token Index: 659

Text #19

Max Range: 5.7489. Min Range: -5.7489

Max Act: 5.0059. Min Act: -0.0000

Data Index: 207995 (The Pile)

Max Activating Token Index: 54