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

Dataset: The Pile

Neuron 4799 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: 1.2874. Min Range: -1.2874

Max Act: 1.2693. Min Act: -0.0000

Data Index: 1609920 (The Pile)

Max Activating Token Index: 961

Text #1

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2874. Min Act: -0.0000

Data Index: 193470 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1692. Min Act: -0.0000

Data Index: 1850817 (The Pile)

Max Activating Token Index: 8

Text #3

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1560. Min Act: -0.0000

Data Index: 1183135 (The Pile)

Max Activating Token Index: 991

Text #4

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1262602 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2337. Min Act: -0.0000

Data Index: 643012 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2683. Min Act: -0.0000

Data Index: 1904320 (The Pile)

Max Activating Token Index: 584

Text #7

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.0831. Min Act: -0.0000

Data Index: 1196920 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2171. Min Act: -0.0000

Data Index: 1795267 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.0632. Min Act: -0.0000

Data Index: 1179597 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1317. Min Act: -0.0000

Data Index: 1425430 (The Pile)

Max Activating Token Index: 585

Text #11

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1001. Min Act: -0.0000

Data Index: 394827 (The Pile)

Max Activating Token Index: 906

Text #12

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1680. Min Act: -0.0000

Data Index: 987722 (The Pile)

Max Activating Token Index: 800

Text #13

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.0547. Min Act: -0.0000

Data Index: 556279 (The Pile)

Max Activating Token Index: 139

Text #14

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1098. Min Act: -0.0000

Data Index: 525492 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.0326. Min Act: -0.0000

Data Index: 712652 (The Pile)

Max Activating Token Index: 1006

Text #16

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1615. Min Act: -0.0000

Data Index: 12829 (The Pile)

Max Activating Token Index: 583

Text #17

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1190. Min Act: -0.0000

Data Index: 551251 (The Pile)

Max Activating Token Index: 977

Text #18

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1135. Min Act: 0.0000

Data Index: 819076 (The Pile)

Max Activating Token Index: 347

Text #19

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.0721. Min Act: 0.0000

Data Index: 129223 (The Pile)

Max Activating Token Index: 589