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

Dataset: The Pile

Neuron 4933 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.6171. Min Act: -0.0000

Data Index: 517521 (The Pile)

Max Activating Token Index: 727

Text #1

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1476250 (The Pile)

Max Activating Token Index: 842

Text #2

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.7073. Min Act: -0.0000

Data Index: 144511 (The Pile)

Max Activating Token Index: 746

Text #3

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1866880 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.6094. Min Act: -0.0000

Data Index: 63870 (The Pile)

Max Activating Token Index: 790

Text #5

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.7032. Min Act: -0.0000

Data Index: 383264 (The Pile)

Max Activating Token Index: 717

Text #6

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1641897 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.6154. Min Act: -0.0000

Data Index: 687136 (The Pile)

Max Activating Token Index: 748

Text #8

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.7610. Min Act: -0.0000

Data Index: 897563 (The Pile)

Max Activating Token Index: 100

Text #9

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1266008 (The Pile)

Max Activating Token Index: 767

Text #10

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.7470. Min Act: -0.0000

Data Index: 1555964 (The Pile)

Max Activating Token Index: 817

Text #11

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.5940. Min Act: -0.0000

Data Index: 1537112 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1944523 (The Pile)

Max Activating Token Index: 848

Text #13

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.6834. Min Act: -0.0000

Data Index: 39168 (The Pile)

Max Activating Token Index: 726

Text #14

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.5937. Min Act: -0.0000

Data Index: 12006 (The Pile)

Max Activating Token Index: 1019

Text #15

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1183386 (The Pile)

Max Activating Token Index: 990

Text #16

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1915014 (The Pile)

Max Activating Token Index: 717

Text #17

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1208388 (The Pile)

Max Activating Token Index: 661

Text #18

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1722858 (The Pile)

Max Activating Token Index: 948

Text #19

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1445338 (The Pile)

Max Activating Token Index: 408