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

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

Neuron 476 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.8711. Min Act: -0.0000

Data Index: 951374 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.8773. Min Act: -0.0000

Data Index: 263316 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1249149 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7698. Min Act: -0.0000

Data Index: 530611 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6921. Min Act: -0.0000

Data Index: 193368 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6937. Min Act: -0.0000

Data Index: 235193 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6481. Min Act: -0.0000

Data Index: 897045 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7185. Min Act: -0.0000

Data Index: 352097 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1199673 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6860. Min Act: -0.0000

Data Index: 358799 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6394. Min Act: -0.0000

Data Index: 787053 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6312. Min Act: -0.0000

Data Index: 958849 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6057. Min Act: -0.0000

Data Index: 542388 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1308760 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.5722. Min Act: -0.0000

Data Index: 308501 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.5959. Min Act: -0.0000

Data Index: 392492 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6160. Min Act: -0.0000

Data Index: 352708 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.5942. Min Act: -0.0000

Data Index: 555489 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.5726. Min Act: -0.0000

Data Index: 262919 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1003331 (C4 (Web Text))

Max Activating Token Index: 77