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

Dataset: The Pile

Neuron 1572 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: 1.7460. Min Range: -1.7460

Max Act: 1.7460. Min Act: -0.0000

Data Index: 1102525 (The Pile)

Max Activating Token Index: 597

Text #1

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.7352. Min Act: -0.0000

Data Index: 785862 (The Pile)

Max Activating Token Index: 897

Text #2

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.4760. Min Act: -0.0000

Data Index: 1375128 (The Pile)

Max Activating Token Index: 734

Text #3

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.4984. Min Act: -0.0000

Data Index: 961262 (The Pile)

Max Activating Token Index: 525

Text #4

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.5481. Min Act: -0.0000

Data Index: 171193 (The Pile)

Max Activating Token Index: 934

Text #5

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.4276. Min Act: -0.0000

Data Index: 1096020 (The Pile)

Max Activating Token Index: 888

Text #6

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.3080. Min Act: -0.0000

Data Index: 824561 (The Pile)

Max Activating Token Index: 819

Text #7

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.3710. Min Act: -0.0000

Data Index: 591404 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.2931. Min Act: 0.0000

Data Index: 1330700 (The Pile)

Max Activating Token Index: 900

Text #9

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.2980. Min Act: -0.0000

Data Index: 1892682 (The Pile)

Max Activating Token Index: 887

Text #10

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.2342. Min Act: -0.0000

Data Index: 773970 (The Pile)

Max Activating Token Index: 191

Text #11

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.2577. Min Act: -0.0000

Data Index: 1856107 (The Pile)

Max Activating Token Index: 255

Text #12

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.2791. Min Act: -0.0000

Data Index: 32548 (The Pile)

Max Activating Token Index: 926

Text #13

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.2944. Min Act: -0.0000

Data Index: 1086458 (The Pile)

Max Activating Token Index: 832

Text #14

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.2084. Min Act: -0.0000

Data Index: 35842 (The Pile)

Max Activating Token Index: 659

Text #15

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.2793. Min Act: -0.0000

Data Index: 10939 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.2655. Min Act: -0.0000

Data Index: 24752 (The Pile)

Max Activating Token Index: 838

Text #17

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.2595. Min Act: -0.0000

Data Index: 1810231 (The Pile)

Max Activating Token Index: 449

Text #18

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.3348. Min Act: -0.0000

Data Index: 924887 (The Pile)

Max Activating Token Index: 1019

Text #19

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.1729. Min Act: -0.0000

Data Index: 1294802 (The Pile)

Max Activating Token Index: 951