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

Dataset: The Pile

Neuron 74 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1878902 (The Pile)

Max Activating Token Index: 508

Text #1

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.5234. Min Act: -0.0000

Data Index: 667609 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4140. Min Act: -0.0000

Data Index: 1102810 (The Pile)

Max Activating Token Index: 43

Text #3

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1946822 (The Pile)

Max Activating Token Index: 308

Text #4

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1799848 (The Pile)

Max Activating Token Index: 10

Text #5

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.3710. Min Act: -0.0000

Data Index: 1572360 (The Pile)

Max Activating Token Index: 947

Text #6

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4027. Min Act: -0.0000

Data Index: 832266 (The Pile)

Max Activating Token Index: 41

Text #7

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4107. Min Act: -0.0000

Data Index: 639657 (The Pile)

Max Activating Token Index: 10

Text #8

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.3761. Min Act: -0.0000

Data Index: 53999 (The Pile)

Max Activating Token Index: 49

Text #9

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4006. Min Act: -0.0000

Data Index: 1951260 (The Pile)

Max Activating Token Index: 433

Text #10

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1029472 (The Pile)

Max Activating Token Index: 982

Text #11

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.3394. Min Act: -0.0000

Data Index: 561931 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.3765. Min Act: -0.0000

Data Index: 838220 (The Pile)

Max Activating Token Index: 585

Text #13

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.3520. Min Act: -0.0000

Data Index: 43662 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.2341. Min Act: -0.0000

Data Index: 648661 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1680319 (The Pile)

Max Activating Token Index: 931

Text #16

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.3328. Min Act: -0.0000

Data Index: 344249 (The Pile)

Max Activating Token Index: 425

Text #17

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.2951. Min Act: -0.0000

Data Index: 942945 (The Pile)

Max Activating Token Index: 911

Text #18

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.3079. Min Act: -0.0000

Data Index: 517055 (The Pile)

Max Activating Token Index: 142

Text #19

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.3146. Min Act: -0.0000

Data Index: 1920062 (The Pile)

Max Activating Token Index: 697