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

Dataset: The Pile

Neuron 3360 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.4501. Min Act: -0.0000

Data Index: 1111217 (The Pile)

Max Activating Token Index: 103

Text #1

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.6147. Min Act: -0.0000

Data Index: 305899 (The Pile)

Max Activating Token Index: 798

Text #2

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.3757. Min Act: -0.0000

Data Index: 630605 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.4148. Min Act: -0.0000

Data Index: 1284468 (The Pile)

Max Activating Token Index: 597

Text #4

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.3794. Min Act: -0.0000

Data Index: 33634 (The Pile)

Max Activating Token Index: 585

Text #5

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.1030. Min Act: -0.0000

Data Index: 19437 (The Pile)

Max Activating Token Index: 41

Text #6

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.2318. Min Act: -0.0000

Data Index: 1826159 (The Pile)

Max Activating Token Index: 860

Text #7

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.3789. Min Act: -0.0000

Data Index: 1333981 (The Pile)

Max Activating Token Index: 77

Text #8

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.3190. Min Act: -0.0000

Data Index: 239826 (The Pile)

Max Activating Token Index: 696

Text #9

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.3432. Min Act: -0.0000

Data Index: 1107315 (The Pile)

Max Activating Token Index: 576

Text #10

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.2407. Min Act: -0.0000

Data Index: 1113914 (The Pile)

Max Activating Token Index: 21

Text #11

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.2609. Min Act: -0.0000

Data Index: 457262 (The Pile)

Max Activating Token Index: 489

Text #12

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.1037. Min Act: -0.0000

Data Index: 1303621 (The Pile)

Max Activating Token Index: 804

Text #13

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.1507. Min Act: 0.0000

Data Index: 910447 (The Pile)

Max Activating Token Index: 811

Text #14

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.2104. Min Act: -0.0000

Data Index: 1126278 (The Pile)

Max Activating Token Index: 214

Text #15

Max Range: 3.6147. Min Range: -3.6147

Max Act: 2.6256. Min Act: -0.0000

Data Index: 377325 (The Pile)

Max Activating Token Index: 996

Text #16

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.1862. Min Act: 0.0000

Data Index: 1578600 (The Pile)

Max Activating Token Index: 847

Text #17

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.1609. Min Act: 0.0000

Data Index: 271286 (The Pile)

Max Activating Token Index: 970

Text #18

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.1717. Min Act: 0.0000

Data Index: 1532717 (The Pile)

Max Activating Token Index: 922

Text #19

Max Range: 3.6147. Min Range: -3.6147

Max Act: 3.0037. Min Act: -0.0000

Data Index: 1055964 (The Pile)

Max Activating Token Index: 281