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

Dataset: The Pile

Neuron 2249 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: 0.6423. Min Range: -0.6423

Max Act: 0.6423. Min Act: -0.0000

Data Index: 1677985 (The Pile)

Max Activating Token Index: 841

Text #1

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.6100. Min Act: -0.0000

Data Index: 1275585 (The Pile)

Max Activating Token Index: 888

Text #2

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5909. Min Act: -0.0000

Data Index: 818788 (The Pile)

Max Activating Token Index: 927

Text #3

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5602. Min Act: -0.0000

Data Index: 112345 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.6060. Min Act: -0.0000

Data Index: 173531 (The Pile)

Max Activating Token Index: 362

Text #5

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1090321 (The Pile)

Max Activating Token Index: 994

Text #6

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1558420 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1919449 (The Pile)

Max Activating Token Index: 886

Text #8

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5238. Min Act: -0.0000

Data Index: 731666 (The Pile)

Max Activating Token Index: 838

Text #9

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1289959 (The Pile)

Max Activating Token Index: 446

Text #10

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1080114 (The Pile)

Max Activating Token Index: 222

Text #11

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4703. Min Act: -0.0000

Data Index: 186080 (The Pile)

Max Activating Token Index: 644

Text #12

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1036974 (The Pile)

Max Activating Token Index: 909

Text #13

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4900. Min Act: -0.0000

Data Index: 1451074 (The Pile)

Max Activating Token Index: 250

Text #14

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1138301 (The Pile)

Max Activating Token Index: 857

Text #15

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4994. Min Act: -0.0000

Data Index: 943590 (The Pile)

Max Activating Token Index: 903

Text #16

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1617786 (The Pile)

Max Activating Token Index: 504

Text #17

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1134723 (The Pile)

Max Activating Token Index: 1014

Text #18

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1005426 (The Pile)

Max Activating Token Index: 841

Text #19

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4433. Min Act: -0.0000

Data Index: 1947833 (The Pile)

Max Activating Token Index: 631