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

Dataset: The Pile

Neuron 4005 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: 0.9050. Min Range: -0.9050

Max Act: 0.8588. Min Act: -0.0000

Data Index: 1647963 (The Pile)

Max Activating Token Index: 124

Text #1

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.9050. Min Act: -0.0000

Data Index: 1793972 (The Pile)

Max Activating Token Index: 275

Text #2

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8745. Min Act: -0.0000

Data Index: 280433 (The Pile)

Max Activating Token Index: 880

Text #3

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8793. Min Act: -0.0000

Data Index: 46685 (The Pile)

Max Activating Token Index: 24

Text #4

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8608. Min Act: -0.0000

Data Index: 123894 (The Pile)

Max Activating Token Index: 151

Text #5

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1694971 (The Pile)

Max Activating Token Index: 777

Text #6

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8401. Min Act: -0.0000

Data Index: 883498 (The Pile)

Max Activating Token Index: 888

Text #7

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8177. Min Act: -0.0000

Data Index: 333258 (The Pile)

Max Activating Token Index: 61

Text #8

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7876. Min Act: -0.0000

Data Index: 722309 (The Pile)

Max Activating Token Index: 641

Text #9

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1407852 (The Pile)

Max Activating Token Index: 1013

Text #10

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8078. Min Act: -0.0000

Data Index: 974215 (The Pile)

Max Activating Token Index: 19

Text #11

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1276700 (The Pile)

Max Activating Token Index: 226

Text #12

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7625. Min Act: -0.0000

Data Index: 993468 (The Pile)

Max Activating Token Index: 153

Text #13

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6724. Min Act: -0.0000

Data Index: 440174 (The Pile)

Max Activating Token Index: 784

Text #14

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8053. Min Act: -0.0000

Data Index: 1665930 (The Pile)

Max Activating Token Index: 154

Text #15

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1152010 (The Pile)

Max Activating Token Index: 21

Text #16

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1451951 (The Pile)

Max Activating Token Index: 923

Text #17

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6579. Min Act: -0.0000

Data Index: 1569072 (The Pile)

Max Activating Token Index: 173

Text #18

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6476. Min Act: -0.0000

Data Index: 778182 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6565. Min Act: -0.0000

Data Index: 77077 (The Pile)

Max Activating Token Index: 90