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

Dataset: The Pile

Neuron 2467 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.4146. Min Act: -0.0000

Data Index: 906405 (The Pile)

Max Activating Token Index: 769

Text #1

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.4022. Min Act: -0.0000

Data Index: 180440 (The Pile)

Max Activating Token Index: 786

Text #2

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3836. Min Act: -0.0000

Data Index: 1986617 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3796. Min Act: -0.0000

Data Index: 95195 (The Pile)

Max Activating Token Index: 853

Text #4

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.4006. Min Act: -0.0000

Data Index: 81563 (The Pile)

Max Activating Token Index: 766

Text #5

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1979300 (The Pile)

Max Activating Token Index: 662

Text #6

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3599. Min Act: -0.0000

Data Index: 1287137 (The Pile)

Max Activating Token Index: 184

Text #7

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1359283 (The Pile)

Max Activating Token Index: 488

Text #8

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.4023. Min Act: -0.0000

Data Index: 315847 (The Pile)

Max Activating Token Index: 793

Text #9

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3614. Min Act: -0.0000

Data Index: 26074 (The Pile)

Max Activating Token Index: 654

Text #10

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1188326 (The Pile)

Max Activating Token Index: 336

Text #11

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3455. Min Act: -0.0000

Data Index: 1784493 (The Pile)

Max Activating Token Index: 175

Text #12

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3757. Min Act: -0.0000

Data Index: 61901 (The Pile)

Max Activating Token Index: 160

Text #13

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3352. Min Act: -0.0000

Data Index: 683871 (The Pile)

Max Activating Token Index: 225

Text #14

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3353. Min Act: -0.0000

Data Index: 575510 (The Pile)

Max Activating Token Index: 57

Text #15

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3460. Min Act: -0.0000

Data Index: 277784 (The Pile)

Max Activating Token Index: 728

Text #16

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1130153 (The Pile)

Max Activating Token Index: 845

Text #17

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1424068 (The Pile)

Max Activating Token Index: 523

Text #18

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3622. Min Act: -0.0000

Data Index: 884104 (The Pile)

Max Activating Token Index: 882

Text #19

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1628830 (The Pile)

Max Activating Token Index: 736