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

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

Neuron 4970 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.8694. Min Act: -0.0000

Data Index: 382698 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.8320. Min Act: -0.0000

Data Index: 635334 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.7680. Min Act: -0.0000

Data Index: 538871 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1161464 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1100570 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.7740. Min Act: -0.0000

Data Index: 42261 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.8748. Min Act: -0.0000

Data Index: 291412 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.7057. Min Act: -0.0000

Data Index: 916340 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1225441 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.7720. Min Act: -0.0000

Data Index: 1083126 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.7214. Min Act: -0.0000

Data Index: 1298262 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.7735. Min Act: -0.0000

Data Index: 968101 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.7312. Min Act: -0.0000

Data Index: 1190392 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.7477. Min Act: -0.0000

Data Index: 738231 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.5676. Min Act: -0.0000

Data Index: 681165 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.5559. Min Act: -0.0000

Data Index: 338424 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.6780. Min Act: -0.0000

Data Index: 396781 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.6178. Min Act: -0.0000

Data Index: 186921 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1158706 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.6415. Min Act: -0.0000

Data Index: 981592 (C4 (Web Text))

Max Activating Token Index: 626