Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3650 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.9385. Min Act: -0.0000

Data Index: 440819 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.9961. Min Act: -0.0000

Data Index: 759888 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.9643. Min Act: -0.0000

Data Index: 1195738 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.9224. Min Act: -0.0000

Data Index: 101246 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8538. Min Act: -0.0000

Data Index: 794699 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.9952. Min Act: -0.0000

Data Index: 678509 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.9504. Min Act: -0.0000

Data Index: 519273 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8662. Min Act: -0.0000

Data Index: 753498 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.9149. Min Act: -0.0000

Data Index: 331561 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.9155. Min Act: -0.0000

Data Index: 875180 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8325. Min Act: -0.0000

Data Index: 716589 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7899. Min Act: -0.0000

Data Index: 693262 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1259292 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7888. Min Act: -0.0000

Data Index: 358946 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8046. Min Act: -0.0000

Data Index: 248217 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8372. Min Act: -0.0000

Data Index: 32515 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7792. Min Act: 0.0000

Data Index: 588880 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8934. Min Act: -0.0000

Data Index: 1017664 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8008. Min Act: 0.0000

Data Index: 596861 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7275. Min Act: -0.0000

Data Index: 786165 (C4 (Web Text))

Max Activating Token Index: 800