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

Dataset: The Pile

Neuron 817 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0465. Min Range: -7.0465

Max Act: 7.0465. Min Act: -0.0000

Data Index: 1929973 (The Pile)

Max Activating Token Index: 830

Text #1

Max Range: 7.0465. Min Range: -7.0465

Max Act: 7.0403. Min Act: -0.0000

Data Index: 933848 (The Pile)

Max Activating Token Index: 755

Text #2

Max Range: 7.0465. Min Range: -7.0465

Max Act: 6.8640. Min Act: -0.0000

Data Index: 211387 (The Pile)

Max Activating Token Index: 1018

Text #3

Max Range: 7.0465. Min Range: -7.0465

Max Act: 7.0358. Min Act: -0.0000

Data Index: 679655 (The Pile)

Max Activating Token Index: 775

Text #4

Max Range: 7.0465. Min Range: -7.0465

Max Act: 7.0276. Min Act: -0.0000

Data Index: 486982 (The Pile)

Max Activating Token Index: 685

Text #5

Max Range: 7.0465. Min Range: -7.0465

Max Act: 6.4810. Min Act: -0.0000

Data Index: 230241 (The Pile)

Max Activating Token Index: 817

Text #6

Max Range: 7.0465. Min Range: -7.0465

Max Act: 6.3975. Min Act: -0.0000

Data Index: 1876618 (The Pile)

Max Activating Token Index: 884

Text #7

Max Range: 7.0465. Min Range: -7.0465

Max Act: 6.5098. Min Act: -0.0000

Data Index: 1729267 (The Pile)

Max Activating Token Index: 1006

Text #8

Max Range: 7.0465. Min Range: -7.0465

Max Act: 6.4475. Min Act: -0.0000

Data Index: 1618477 (The Pile)

Max Activating Token Index: 913

Text #9

Max Range: 7.0465. Min Range: -7.0465

Max Act: 6.6303. Min Act: -0.0000

Data Index: 888368 (The Pile)

Max Activating Token Index: 241

Text #10

Max Range: 7.0465. Min Range: -7.0465

Max Act: 6.7370. Min Act: -0.0000

Data Index: 876359 (The Pile)

Max Activating Token Index: 496

Text #11

Max Range: 7.0465. Min Range: -7.0465

Max Act: 6.5474. Min Act: -0.0000

Data Index: 360689 (The Pile)

Max Activating Token Index: 41

Text #12

Max Range: 7.0465. Min Range: -7.0465

Max Act: 6.4982. Min Act: -0.0000

Data Index: 1713612 (The Pile)

Max Activating Token Index: 940

Text #13

Max Range: 7.0465. Min Range: -7.0465

Max Act: 6.3306. Min Act: -0.0000

Data Index: 134212 (The Pile)

Max Activating Token Index: 758

Text #14

Max Range: 7.0465. Min Range: -7.0465

Max Act: 5.9528. Min Act: -0.0000

Data Index: 597542 (The Pile)

Max Activating Token Index: 730

Text #15

Max Range: 7.0465. Min Range: -7.0465

Max Act: 6.3533. Min Act: -0.0000

Data Index: 669939 (The Pile)

Max Activating Token Index: 633

Text #16

Max Range: 7.0465. Min Range: -7.0465

Max Act: 6.3956. Min Act: -0.0000

Data Index: 1451709 (The Pile)

Max Activating Token Index: 502

Text #17

Max Range: 7.0465. Min Range: -7.0465

Max Act: 6.5439. Min Act: -0.0000

Data Index: 562068 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 7.0465. Min Range: -7.0465

Max Act: 6.1913. Min Act: -0.0000

Data Index: 1600319 (The Pile)

Max Activating Token Index: 16

Text #19

Max Range: 7.0465. Min Range: -7.0465

Max Act: 6.2292. Min Act: -0.0000

Data Index: 363137 (The Pile)

Max Activating Token Index: 539