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

Dataset: The Pile

Neuron 3038 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0884. Min Range: -1.0884

Max Act: 1.0884. Min Act: -0.0000

Data Index: 729641 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.9813. Min Act: -0.0000

Data Index: 1185827 (The Pile)

Max Activating Token Index: 416

Text #2

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1158674 (The Pile)

Max Activating Token Index: 445

Text #3

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8328. Min Act: -0.0000

Data Index: 1379472 (The Pile)

Max Activating Token Index: 138

Text #4

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7884. Min Act: -0.0000

Data Index: 882549 (The Pile)

Max Activating Token Index: 996

Text #5

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7929. Min Act: -0.0000

Data Index: 851472 (The Pile)

Max Activating Token Index: 243

Text #6

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7521. Min Act: -0.0000

Data Index: 1112694 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7518. Min Act: -0.0000

Data Index: 964642 (The Pile)

Max Activating Token Index: 255

Text #8

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7054. Min Act: -0.0000

Data Index: 199633 (The Pile)

Max Activating Token Index: 23

Text #9

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1878608 (The Pile)

Max Activating Token Index: 688

Text #10

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.6512. Min Act: -0.0000

Data Index: 506008 (The Pile)

Max Activating Token Index: 302

Text #11

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.6115. Min Act: -0.0000

Data Index: 9473 (The Pile)

Max Activating Token Index: 332

Text #12

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1403959 (The Pile)

Max Activating Token Index: 30

Text #13

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.5807. Min Act: -0.0000

Data Index: 1191112 (The Pile)

Max Activating Token Index: 134

Text #14

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1637984 (The Pile)

Max Activating Token Index: 148

Text #15

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1123301 (The Pile)

Max Activating Token Index: 52

Text #16

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1349186 (The Pile)

Max Activating Token Index: 106

Text #17

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.5969. Min Act: -0.0000

Data Index: 709292 (The Pile)

Max Activating Token Index: 546

Text #18

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.5609. Min Act: -0.0000

Data Index: 311397 (The Pile)

Max Activating Token Index: 970

Text #19

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1952621 (The Pile)

Max Activating Token Index: 257