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

Dataset: The Pile

Neuron 3460 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1868683 (The Pile)

Max Activating Token Index: 200

Text #1

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.6305. Min Act: -0.0000

Data Index: 10599 (The Pile)

Max Activating Token Index: 824

Text #2

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5861. Min Act: -0.0000

Data Index: 161315 (The Pile)

Max Activating Token Index: 786

Text #3

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1576854 (The Pile)

Max Activating Token Index: 447

Text #4

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5601. Min Act: -0.0000

Data Index: 1887314 (The Pile)

Max Activating Token Index: 387

Text #5

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1047759 (The Pile)

Max Activating Token Index: 405

Text #6

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5109. Min Act: -0.0000

Data Index: 358844 (The Pile)

Max Activating Token Index: 363

Text #7

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5057. Min Act: -0.0000

Data Index: 1452201 (The Pile)

Max Activating Token Index: 900

Text #8

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5608. Min Act: -0.0000

Data Index: 1430583 (The Pile)

Max Activating Token Index: 913

Text #9

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5116. Min Act: -0.0000

Data Index: 112101 (The Pile)

Max Activating Token Index: 989

Text #10

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4722. Min Act: -0.0000

Data Index: 566975 (The Pile)

Max Activating Token Index: 867

Text #11

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5147. Min Act: -0.0000

Data Index: 223545 (The Pile)

Max Activating Token Index: 739

Text #12

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1903839 (The Pile)

Max Activating Token Index: 639

Text #13

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4362. Min Act: -0.0000

Data Index: 35627 (The Pile)

Max Activating Token Index: 808

Text #14

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4779. Min Act: -0.0000

Data Index: 408599 (The Pile)

Max Activating Token Index: 377

Text #15

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4798. Min Act: -0.0000

Data Index: 730638 (The Pile)

Max Activating Token Index: 486

Text #16

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5267. Min Act: -0.0000

Data Index: 19437 (The Pile)

Max Activating Token Index: 767

Text #17

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4735. Min Act: -0.0000

Data Index: 926347 (The Pile)

Max Activating Token Index: 668

Text #18

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4456. Min Act: -0.0000

Data Index: 970458 (The Pile)

Max Activating Token Index: 180

Text #19

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4603. Min Act: -0.0000

Data Index: 21535 (The Pile)

Max Activating Token Index: 634