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

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

Neuron 1836 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: 4.1875. Min Range: -4.1875

Max Act: 4.0444. Min Act: -0.0000

Data Index: 1306825 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 4.1875. Min Range: -4.1875

Max Act: 4.1875. Min Act: -0.0000

Data Index: 1107595 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 4.1875. Min Range: -4.1875

Max Act: 3.8324. Min Act: -0.0000

Data Index: 221463 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 4.1875. Min Range: -4.1875

Max Act: 3.5470. Min Act: -0.0000

Data Index: 707808 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 4.1875. Min Range: -4.1875

Max Act: 3.4458. Min Act: -0.0000

Data Index: 9470 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 4.1875. Min Range: -4.1875

Max Act: 3.4437. Min Act: -0.0000

Data Index: 1325404 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 4.1875. Min Range: -4.1875

Max Act: 3.1380. Min Act: -0.0000

Data Index: 549087 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 4.1875. Min Range: -4.1875

Max Act: 3.2824. Min Act: -0.0000

Data Index: 1252656 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 4.1875. Min Range: -4.1875

Max Act: 3.1483. Min Act: -0.0000

Data Index: 1156532 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 4.1875. Min Range: -4.1875

Max Act: 3.1013. Min Act: -0.0000

Data Index: 529137 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 4.1875. Min Range: -4.1875

Max Act: 2.9542. Min Act: -0.0000

Data Index: 801253 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 4.1875. Min Range: -4.1875

Max Act: 3.2193. Min Act: -0.0000

Data Index: 759973 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 4.1875. Min Range: -4.1875

Max Act: 3.0405. Min Act: -0.0000

Data Index: 1042605 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 4.1875. Min Range: -4.1875

Max Act: 3.0215. Min Act: -0.0000

Data Index: 1058033 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 4.1875. Min Range: -4.1875

Max Act: 3.0102. Min Act: -0.0000

Data Index: 1090141 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 4.1875. Min Range: -4.1875

Max Act: 3.1473. Min Act: -0.0000

Data Index: 996407 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 4.1875. Min Range: -4.1875

Max Act: 2.9959. Min Act: -0.0000

Data Index: 575549 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 4.1875. Min Range: -4.1875

Max Act: 2.9543. Min Act: -0.0000

Data Index: 213321 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 4.1875. Min Range: -4.1875

Max Act: 2.9548. Min Act: -0.0000

Data Index: 1125273 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 4.1875. Min Range: -4.1875

Max Act: 2.8078. Min Act: -0.0000

Data Index: 333127 (C4 (Web Text))

Max Activating Token Index: 641