Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2903 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1930. Min Range: -2.1930

Max Act: 2.1625. Min Act: -0.0000

Data Index: 512808 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 2.1930. Min Range: -2.1930

Max Act: 2.1930. Min Act: -0.0000

Data Index: 164602 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 2.1930. Min Range: -2.1930

Max Act: 1.9580. Min Act: -0.0000

Data Index: 210812 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 2.1930. Min Range: -2.1930

Max Act: 1.9709. Min Act: -0.0000

Data Index: 553241 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 2.1930. Min Range: -2.1930

Max Act: 1.8671. Min Act: -0.0000

Data Index: 1048148 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 2.1930. Min Range: -2.1930

Max Act: 1.8576. Min Act: -0.0000

Data Index: 1076884 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 2.1930. Min Range: -2.1930

Max Act: 1.8417. Min Act: -0.0000

Data Index: 47977 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 2.1930. Min Range: -2.1930

Max Act: 1.6828. Min Act: -0.0000

Data Index: 956686 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 2.1930. Min Range: -2.1930

Max Act: 1.8815. Min Act: -0.0000

Data Index: 640076 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 2.1930. Min Range: -2.1930

Max Act: 1.7539. Min Act: -0.0000

Data Index: 100849 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 2.1930. Min Range: -2.1930

Max Act: 1.6596. Min Act: -0.0000

Data Index: 941510 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 2.1930. Min Range: -2.1930

Max Act: 1.7521. Min Act: -0.0000

Data Index: 1247758 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 2.1930. Min Range: -2.1930

Max Act: 1.6472. Min Act: -0.0000

Data Index: 1347631 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 2.1930. Min Range: -2.1930

Max Act: 1.6456. Min Act: -0.0000

Data Index: 288766 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 2.1930. Min Range: -2.1930

Max Act: 1.6451. Min Act: -0.0000

Data Index: 1066469 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 2.1930. Min Range: -2.1930

Max Act: 1.7335. Min Act: -0.0000

Data Index: 696047 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 2.1930. Min Range: -2.1930

Max Act: 1.7051. Min Act: -0.0000

Data Index: 333639 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 2.1930. Min Range: -2.1930

Max Act: 1.7002. Min Act: 0.0000

Data Index: 592746 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 2.1930. Min Range: -2.1930

Max Act: 1.5750. Min Act: -0.0000

Data Index: 819717 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 2.1930. Min Range: -2.1930

Max Act: 1.6560. Min Act: -0.0000

Data Index: 952235 (C4 (Web Text))

Max Activating Token Index: 202