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

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

Neuron 5690 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: 4.6788. Min Range: -4.6788

Max Act: 4.5109. Min Act: -0.0000

Data Index: 840065 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.6788. Min Act: -0.0000

Data Index: 569674 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.5565. Min Act: -0.0000

Data Index: 778797 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.5910. Min Act: -0.0000

Data Index: 102244 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.2142. Min Act: -0.0000

Data Index: 303282 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.4133. Min Act: -0.0000

Data Index: 463014 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.3377. Min Act: -0.0000

Data Index: 392795 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.3329. Min Act: -0.0000

Data Index: 192698 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.5103. Min Act: -0.0000

Data Index: 1124150 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.3503. Min Act: -0.0000

Data Index: 1039788 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.3223. Min Act: -0.0000

Data Index: 949001 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.3248. Min Act: -0.0000

Data Index: 254057 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.2983. Min Act: -0.0000

Data Index: 1078615 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.2734. Min Act: -0.0000

Data Index: 1248708 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.2235. Min Act: -0.0000

Data Index: 728628 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.2289. Min Act: -0.0000

Data Index: 453212 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.2146. Min Act: -0.0000

Data Index: 861172 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.1686. Min Act: -0.0000

Data Index: 1029806 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.3411. Min Act: -0.0000

Data Index: 424824 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 4.6788. Min Range: -4.6788

Max Act: 4.0992. Min Act: -0.0000

Data Index: 1323098 (C4 (Web Text))

Max Activating Token Index: 950