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

Dataset: The Pile

Neuron 2218 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: 0.3721. Min Range: -0.3721

Max Act: 0.3438. Min Act: -0.0000

Data Index: 295074 (The Pile)

Max Activating Token Index: 977

Text #1

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3721. Min Act: -0.0000

Data Index: 721492 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3397. Min Act: -0.0000

Data Index: 814425 (The Pile)

Max Activating Token Index: 894

Text #3

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3426. Min Act: -0.0000

Data Index: 1742736 (The Pile)

Max Activating Token Index: 946

Text #4

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3003. Min Act: -0.0000

Data Index: 499120 (The Pile)

Max Activating Token Index: 842

Text #5

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3164. Min Act: -0.0000

Data Index: 1809516 (The Pile)

Max Activating Token Index: 800

Text #6

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2936. Min Act: -0.0000

Data Index: 1803942 (The Pile)

Max Activating Token Index: 852

Text #7

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1436712 (The Pile)

Max Activating Token Index: 645

Text #8

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2781. Min Act: -0.0000

Data Index: 502629 (The Pile)

Max Activating Token Index: 858

Text #9

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1701937 (The Pile)

Max Activating Token Index: 884

Text #10

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3111. Min Act: -0.0000

Data Index: 1601183 (The Pile)

Max Activating Token Index: 890

Text #11

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1733831 (The Pile)

Max Activating Token Index: 824

Text #12

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2999. Min Act: -0.0000

Data Index: 1563037 (The Pile)

Max Activating Token Index: 961

Text #13

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3086. Min Act: -0.0000

Data Index: 530767 (The Pile)

Max Activating Token Index: 891

Text #14

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1594169 (The Pile)

Max Activating Token Index: 905

Text #15

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1202871 (The Pile)

Max Activating Token Index: 946

Text #16

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2950. Min Act: -0.0000

Data Index: 261956 (The Pile)

Max Activating Token Index: 903

Text #17

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2692. Min Act: -0.0000

Data Index: 403309 (The Pile)

Max Activating Token Index: 88

Text #18

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2488. Min Act: -0.0000

Data Index: 1182975 (The Pile)

Max Activating Token Index: 622

Text #19

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1321465 (The Pile)

Max Activating Token Index: 955