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

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

Neuron 3006 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.5440. Min Act: -0.0000

Data Index: 260343 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1008474 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4819. Min Act: -0.0000

Data Index: 923791 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4800. Min Act: -0.0000

Data Index: 1196467 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4675. Min Act: -0.0000

Data Index: 1133874 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4654. Min Act: -0.0000

Data Index: 184834 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4441. Min Act: -0.0000

Data Index: 106369 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4654. Min Act: -0.0000

Data Index: 813763 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4507. Min Act: -0.0000

Data Index: 308044 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4384. Min Act: -0.0000

Data Index: 746558 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1291249 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4324. Min Act: -0.0000

Data Index: 447339 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1346583 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4361. Min Act: -0.0000

Data Index: 974501 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4341. Min Act: -0.0000

Data Index: 17854 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4466. Min Act: -0.0000

Data Index: 546147 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4276. Min Act: -0.0000

Data Index: 1148497 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1070907 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4225. Min Act: -0.0000

Data Index: 951064 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4120. Min Act: -0.0000

Data Index: 413873 (C4 (Web Text))

Max Activating Token Index: 585