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

Dataset: The Pile

Neuron 3079 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.7139. Min Act: -0.0000

Data Index: 243175 (The Pile)

Max Activating Token Index: 769

Text #1

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1152477 (The Pile)

Max Activating Token Index: 555

Text #2

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1882336 (The Pile)

Max Activating Token Index: 998

Text #3

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1689897 (The Pile)

Max Activating Token Index: 129

Text #4

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6301. Min Act: -0.0000

Data Index: 995002 (The Pile)

Max Activating Token Index: 967

Text #5

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5967. Min Act: -0.0000

Data Index: 771652 (The Pile)

Max Activating Token Index: 230

Text #6

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5826. Min Act: -0.0000

Data Index: 85564 (The Pile)

Max Activating Token Index: 710

Text #7

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5861. Min Act: -0.0000

Data Index: 1924198 (The Pile)

Max Activating Token Index: 853

Text #8

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5468. Min Act: -0.0000

Data Index: 385090 (The Pile)

Max Activating Token Index: 834

Text #9

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1677793 (The Pile)

Max Activating Token Index: 669

Text #10

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1966625 (The Pile)

Max Activating Token Index: 564

Text #11

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1673721 (The Pile)

Max Activating Token Index: 1021

Text #12

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5184. Min Act: -0.0000

Data Index: 336558 (The Pile)

Max Activating Token Index: 325

Text #13

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6048. Min Act: -0.0000

Data Index: 105152 (The Pile)

Max Activating Token Index: 987

Text #14

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1186932 (The Pile)

Max Activating Token Index: 117

Text #15

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1453837 (The Pile)

Max Activating Token Index: 963

Text #16

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1618016 (The Pile)

Max Activating Token Index: 1014

Text #17

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.4863. Min Act: -0.0000

Data Index: 675050 (The Pile)

Max Activating Token Index: 489

Text #18

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1782121 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5054. Min Act: -0.0000

Data Index: 245446 (The Pile)

Max Activating Token Index: 895