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

Dataset: The Pile

Neuron 1818 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.9969. Min Act: -0.0000

Data Index: 972568 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8005. Min Act: -0.0000

Data Index: 133318 (The Pile)

Max Activating Token Index: 102

Text #2

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.3625. Min Act: -0.0000

Data Index: 738177 (The Pile)

Max Activating Token Index: 85

Text #3

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.4179. Min Act: -0.0000

Data Index: 567070 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.2403. Min Act: -0.0000

Data Index: 1518718 (The Pile)

Max Activating Token Index: 426

Text #5

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.1092. Min Act: -0.0000

Data Index: 1818992 (The Pile)

Max Activating Token Index: 464

Text #6

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.0203. Min Act: -0.0000

Data Index: 222082 (The Pile)

Max Activating Token Index: 93

Text #7

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.1201. Min Act: -0.0000

Data Index: 1978251 (The Pile)

Max Activating Token Index: 666

Text #8

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.1858. Min Act: -0.0000

Data Index: 385705 (The Pile)

Max Activating Token Index: 443

Text #9

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.2139. Min Act: -0.0000

Data Index: 70173 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.3753. Min Act: -0.0000

Data Index: 687889 (The Pile)

Max Activating Token Index: 293

Text #11

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.1816. Min Act: -0.0000

Data Index: 1601744 (The Pile)

Max Activating Token Index: 85

Text #12

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.0939. Min Act: -0.0000

Data Index: 939426 (The Pile)

Max Activating Token Index: 114

Text #13

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.0124. Min Act: -0.0000

Data Index: 332568 (The Pile)

Max Activating Token Index: 845

Text #14

Max Range: 3.9969. Min Range: -3.9969

Max Act: 2.9989. Min Act: -0.0000

Data Index: 1715282 (The Pile)

Max Activating Token Index: 127

Text #15

Max Range: 3.9969. Min Range: -3.9969

Max Act: 2.9009. Min Act: -0.0000

Data Index: 1106723 (The Pile)

Max Activating Token Index: 436

Text #16

Max Range: 3.9969. Min Range: -3.9969

Max Act: 2.4846. Min Act: -0.0000

Data Index: 459897 (The Pile)

Max Activating Token Index: 888

Text #17

Max Range: 3.9969. Min Range: -3.9969

Max Act: 2.7866. Min Act: -0.0000

Data Index: 682811 (The Pile)

Max Activating Token Index: 950

Text #18

Max Range: 3.9969. Min Range: -3.9969

Max Act: 2.7106. Min Act: -0.0000

Data Index: 665957 (The Pile)

Max Activating Token Index: 20

Text #19

Max Range: 3.9969. Min Range: -3.9969

Max Act: 2.6924. Min Act: -0.0000

Data Index: 1597321 (The Pile)

Max Activating Token Index: 513