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

Dataset: The Pile

Neuron 2068 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2462. Min Act: -0.0000

Data Index: 506459 (The Pile)

Max Activating Token Index: 206

Text #1

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2483. Min Act: -0.0000

Data Index: 308078 (The Pile)

Max Activating Token Index: 899

Text #2

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2152. Min Act: -0.0000

Data Index: 1259406 (The Pile)

Max Activating Token Index: 446

Text #3

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1388317 (The Pile)

Max Activating Token Index: 52

Text #4

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2207. Min Act: -0.0000

Data Index: 1639859 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2119. Min Act: -0.0000

Data Index: 796385 (The Pile)

Max Activating Token Index: 706

Text #6

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2195. Min Act: -0.0000

Data Index: 901376 (The Pile)

Max Activating Token Index: 21

Text #7

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1088057 (The Pile)

Max Activating Token Index: 915

Text #8

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2308. Min Act: -0.0000

Data Index: 845726 (The Pile)

Max Activating Token Index: 608

Text #9

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1273411 (The Pile)

Max Activating Token Index: 579

Text #10

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2120. Min Act: -0.0000

Data Index: 411592 (The Pile)

Max Activating Token Index: 75

Text #11

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2058. Min Act: -0.0000

Data Index: 368217 (The Pile)

Max Activating Token Index: 321

Text #12

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1967. Min Act: -0.0000

Data Index: 600114 (The Pile)

Max Activating Token Index: 130

Text #13

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2106. Min Act: -0.0000

Data Index: 639642 (The Pile)

Max Activating Token Index: 94

Text #14

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1313975 (The Pile)

Max Activating Token Index: 421

Text #15

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1824814 (The Pile)

Max Activating Token Index: 648

Text #16

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1982. Min Act: -0.0000

Data Index: 345670 (The Pile)

Max Activating Token Index: 573

Text #17

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1896. Min Act: -0.0000

Data Index: 331948 (The Pile)

Max Activating Token Index: 144

Text #18

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2029. Min Act: -0.0000

Data Index: 938120 (The Pile)

Max Activating Token Index: 520

Text #19

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1218104 (The Pile)

Max Activating Token Index: 308