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

Dataset: The Pile

Neuron 970 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: 0.9030. Min Range: -0.9030

Max Act: 0.9030. Min Act: -0.0000

Data Index: 850388 (The Pile)

Max Activating Token Index: 651

Text #1

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.8056. Min Act: -0.0000

Data Index: 778901 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.7312. Min Act: -0.0000

Data Index: 1447573 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.7087. Min Act: -0.0000

Data Index: 830558 (The Pile)

Max Activating Token Index: 752

Text #4

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.7082. Min Act: -0.0000

Data Index: 246107 (The Pile)

Max Activating Token Index: 914

Text #5

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1766379 (The Pile)

Max Activating Token Index: 1019

Text #6

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1822383 (The Pile)

Max Activating Token Index: 918

Text #7

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1004184 (The Pile)

Max Activating Token Index: 708

Text #8

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1537816 (The Pile)

Max Activating Token Index: 551

Text #9

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6404. Min Act: -0.0000

Data Index: 985456 (The Pile)

Max Activating Token Index: 134

Text #10

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6121. Min Act: -0.0000

Data Index: 785732 (The Pile)

Max Activating Token Index: 938

Text #11

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6491. Min Act: -0.0000

Data Index: 229339 (The Pile)

Max Activating Token Index: 172

Text #12

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1233331 (The Pile)

Max Activating Token Index: 729

Text #13

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6171. Min Act: -0.0000

Data Index: 899164 (The Pile)

Max Activating Token Index: 155

Text #14

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5752. Min Act: -0.0000

Data Index: 293803 (The Pile)

Max Activating Token Index: 663

Text #15

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5736. Min Act: -0.0000

Data Index: 640075 (The Pile)

Max Activating Token Index: 805

Text #16

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1277076 (The Pile)

Max Activating Token Index: 860

Text #17

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5899. Min Act: -0.0000

Data Index: 515670 (The Pile)

Max Activating Token Index: 234

Text #18

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1247440 (The Pile)

Max Activating Token Index: 378

Text #19

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5520. Min Act: -0.0000

Data Index: 217359 (The Pile)

Max Activating Token Index: 851