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

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

Neuron 4471 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0989. Min Range: -1.0989

Max Act: 1.0989. Min Act: -0.0000

Data Index: 203952 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1301381 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.7144. Min Act: -0.0000

Data Index: 359487 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1193594 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.6574. Min Act: -0.0000

Data Index: 276642 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.6594. Min Act: -0.0000

Data Index: 942476 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.5777. Min Act: -0.0000

Data Index: 683164 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.5936. Min Act: -0.0000

Data Index: 378982 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.5620. Min Act: -0.0000

Data Index: 777792 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.5422. Min Act: -0.0000

Data Index: 40798 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.5528. Min Act: -0.0000

Data Index: 373366 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.5813. Min Act: -0.0000

Data Index: 1210999 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.4544. Min Act: -0.0000

Data Index: 130528 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.5432. Min Act: -0.0000

Data Index: 647690 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.5007. Min Act: -0.0000

Data Index: 124382 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.5241. Min Act: -0.0000

Data Index: 62963 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.4472. Min Act: -0.0000

Data Index: 500122 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.4151. Min Act: -0.0000

Data Index: 696171 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1553208 (Python Code)

Max Activating Token Index: 543

Text #19

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.4324. Min Act: -0.0000

Data Index: 616315 (C4 (Web Text))

Max Activating Token Index: 109