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

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

Neuron 4001 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7626. Min Range: -2.7626

Max Act: 2.7517. Min Act: -0.0000

Data Index: 799936 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 2.7626. Min Range: -2.7626

Max Act: 2.7626. Min Act: -0.0000

Data Index: 1197767 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 2.7626. Min Range: -2.7626

Max Act: 2.3979. Min Act: -0.0000

Data Index: 256350 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 2.7626. Min Range: -2.7626

Max Act: 2.2138. Min Act: -0.0001

Data Index: 933740 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 2.7626. Min Range: -2.7626

Max Act: 2.2747. Min Act: -0.0001

Data Index: 452807 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 2.7626. Min Range: -2.7626

Max Act: 2.1975. Min Act: -0.0001

Data Index: 894077 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 2.7626. Min Range: -2.7626

Max Act: 2.1263. Min Act: -0.0000

Data Index: 883800 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 2.7626. Min Range: -2.7626

Max Act: 2.2009. Min Act: -0.0001

Data Index: 1351764 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 2.7626. Min Range: -2.7626

Max Act: 2.1634. Min Act: -0.0000

Data Index: 500222 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 2.7626. Min Range: -2.7626

Max Act: 2.2855. Min Act: -0.0000

Data Index: 626150 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 2.7626. Min Range: -2.7626

Max Act: 1.9703. Min Act: -0.0001

Data Index: 431182 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 2.7626. Min Range: -2.7626

Max Act: 2.0434. Min Act: -0.0000

Data Index: 594572 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 2.7626. Min Range: -2.7626

Max Act: 2.1186. Min Act: -0.0000

Data Index: 1071201 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 2.7626. Min Range: -2.7626

Max Act: 2.1357. Min Act: -0.0000

Data Index: 1203993 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 2.7626. Min Range: -2.7626

Max Act: 1.8855. Min Act: -0.0000

Data Index: 1264775 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 2.7626. Min Range: -2.7626

Max Act: 2.0326. Min Act: -0.0001

Data Index: 1021780 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 2.7626. Min Range: -2.7626

Max Act: 1.9243. Min Act: -0.0000

Data Index: 11689 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 2.7626. Min Range: -2.7626

Max Act: 2.2175. Min Act: -0.0001

Data Index: 765140 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 2.7626. Min Range: -2.7626

Max Act: 1.6491. Min Act: -0.0001

Data Index: 328643 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 2.7626. Min Range: -2.7626

Max Act: 1.7236. Min Act: -0.0000

Data Index: 1326419 (C4 (Web Text))

Max Activating Token Index: 879