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

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

Neuron 3239 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2371. Min Range: -1.2371

Max Act: 1.2371. Min Act: -0.0002

Data Index: 963519 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 1.2371. Min Range: -1.2371

Max Act: 1.0612. Min Act: -0.0002

Data Index: 61076 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.9792. Min Act: -0.0002

Data Index: 1058307 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.8649. Min Act: -0.0002

Data Index: 800245 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.8635. Min Act: -0.0002

Data Index: 35039 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.8942. Min Act: -0.0002

Data Index: 453802 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.9329. Min Act: -0.0002

Data Index: 197427 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.8927. Min Act: -0.0002

Data Index: 235270 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.8573. Min Act: -0.0002

Data Index: 1001533 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.8251. Min Act: -0.0002

Data Index: 1191871 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.8439. Min Act: -0.0002

Data Index: 687369 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.7841. Min Act: -0.0002

Data Index: 89515 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.7244. Min Act: -0.0002

Data Index: 1091615 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.6952. Min Act: -0.0002

Data Index: 1086346 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.6622. Min Act: -0.0002

Data Index: 906805 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.6423. Min Act: -0.0002

Data Index: 978948 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.6116. Min Act: -0.0002

Data Index: 1055021 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.6111. Min Act: -0.0002

Data Index: 482887 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.5744. Min Act: -0.0002

Data Index: 731059 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.5418. Min Act: -0.0002

Data Index: 456739 (C4 (Web Text))

Max Activating Token Index: 494