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

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

Neuron 5058 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.6341. Min Act: -0.0000

Data Index: 50561 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1319117 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1007797 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.5586. Min Act: -0.0000

Data Index: 989998 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.5416. Min Act: -0.0000

Data Index: 524665 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1016832 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.5277. Min Act: -0.0000

Data Index: 788034 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1180820 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.5215. Min Act: -0.0000

Data Index: 479370 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.5116. Min Act: -0.0000

Data Index: 48051 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.5032. Min Act: -0.0000

Data Index: 252538 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.4434. Min Act: -0.0000

Data Index: 99979 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1167649 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.4491. Min Act: -0.0000

Data Index: 874273 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.4324. Min Act: -0.0000

Data Index: 1042904 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.4581. Min Act: -0.0000

Data Index: 1207010 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1066870 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.4292. Min Act: -0.0000

Data Index: 585613 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.4512. Min Act: -0.0000

Data Index: 263464 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.6341. Min Range: -0.6341

Max Act: 0.4200. Min Act: -0.0000

Data Index: 1138083 (C4 (Web Text))

Max Activating Token Index: 182