Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2424 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.3038. Min Act: -0.0001

Data Index: 348594 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2718. Min Act: -0.0001

Data Index: 794780 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2720. Min Act: -0.0001

Data Index: 792126 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2710. Min Act: -0.0001

Data Index: 911687 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2672. Min Act: -0.0001

Data Index: 379382 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2415. Min Act: -0.0001

Data Index: 211570 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2117. Min Act: -0.0001

Data Index: 977084 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2209. Min Act: -0.0001

Data Index: 297100 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2337. Min Act: -0.0001

Data Index: 853889 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2123. Min Act: -0.0001

Data Index: 922110 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1960. Min Act: -0.0001

Data Index: 1083175 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2132. Min Act: -0.0001

Data Index: 1185019 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2255. Min Act: -0.0001

Data Index: 74351 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2103. Min Act: -0.0001

Data Index: 1156526 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1706. Min Act: -0.0001

Data Index: 357543 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2071. Min Act: -0.0001

Data Index: 394462 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1913. Min Act: -0.0001

Data Index: 1004169 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1814. Min Act: -0.0001

Data Index: 898041 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1865. Min Act: -0.0001

Data Index: 1330966 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1924. Min Act: -0.0001

Data Index: 497886 (C4 (Web Text))

Max Activating Token Index: 207