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

Dataset: The Pile

Neuron 4357 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0070. Min Range: -5.0070

Max Act: 5.0070. Min Act: 0.0000

Data Index: 1610974 (The Pile)

Max Activating Token Index: 472

Text #1

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.5402. Min Act: -0.0000

Data Index: 1352925 (The Pile)

Max Activating Token Index: 502

Text #2

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.4298. Min Act: 0.0000

Data Index: 1473460 (The Pile)

Max Activating Token Index: 565

Text #3

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.2814. Min Act: -0.0000

Data Index: 242114 (The Pile)

Max Activating Token Index: 879

Text #4

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.2574. Min Act: -0.0000

Data Index: 1304387 (The Pile)

Max Activating Token Index: 705

Text #5

Max Range: 5.0070. Min Range: -5.0070

Max Act: 3.9978. Min Act: -0.0000

Data Index: 1861955 (The Pile)

Max Activating Token Index: 625

Text #6

Max Range: 5.0070. Min Range: -5.0070

Max Act: 3.6930. Min Act: 0.0000

Data Index: 1778386 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 5.0070. Min Range: -5.0070

Max Act: 3.6181. Min Act: -0.0000

Data Index: 1576892 (The Pile)

Max Activating Token Index: 972

Text #8

Max Range: 5.0070. Min Range: -5.0070

Max Act: 3.4481. Min Act: 0.0000

Data Index: 1472861 (The Pile)

Max Activating Token Index: 254

Text #9

Max Range: 5.0070. Min Range: -5.0070

Max Act: 3.4648. Min Act: 0.0000

Data Index: 1246245 (The Pile)

Max Activating Token Index: 745

Text #10

Max Range: 5.0070. Min Range: -5.0070

Max Act: 3.3613. Min Act: 0.0000

Data Index: 1933555 (The Pile)

Max Activating Token Index: 597

Text #11

Max Range: 5.0070. Min Range: -5.0070

Max Act: 3.3762. Min Act: -0.0000

Data Index: 1337795 (The Pile)

Max Activating Token Index: 774

Text #12

Max Range: 5.0070. Min Range: -5.0070

Max Act: 3.2678. Min Act: -0.0000

Data Index: 1581670 (The Pile)

Max Activating Token Index: 679

Text #13

Max Range: 5.0070. Min Range: -5.0070

Max Act: 3.2583. Min Act: 0.0000

Data Index: 456427 (The Pile)

Max Activating Token Index: 19

Text #14

Max Range: 5.0070. Min Range: -5.0070

Max Act: 3.2208. Min Act: -0.0000

Data Index: 488221 (The Pile)

Max Activating Token Index: 640

Text #15

Max Range: 5.0070. Min Range: -5.0070

Max Act: 3.1968. Min Act: 0.0000

Data Index: 1979372 (The Pile)

Max Activating Token Index: 223

Text #16

Max Range: 5.0070. Min Range: -5.0070

Max Act: 3.1487. Min Act: -0.0000

Data Index: 924571 (The Pile)

Max Activating Token Index: 877

Text #17

Max Range: 5.0070. Min Range: -5.0070

Max Act: 3.0975. Min Act: -0.0000

Data Index: 904457 (The Pile)

Max Activating Token Index: 443

Text #18

Max Range: 5.0070. Min Range: -5.0070

Max Act: 3.1062. Min Act: -0.0000

Data Index: 1193938 (The Pile)

Max Activating Token Index: 422

Text #19

Max Range: 5.0070. Min Range: -5.0070

Max Act: 3.0799. Min Act: -0.0000

Data Index: 10939 (The Pile)

Max Activating Token Index: 413