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

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

Neuron 1596 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.2328. Min Act: -0.0000

Data Index: 458889 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.2175. Min Act: -0.0000

Data Index: 497592 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.2049. Min Act: -0.0000

Data Index: 953090 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1330248 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.2030. Min Act: -0.0000

Data Index: 517097 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1953. Min Act: -0.0000

Data Index: 82252 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1867. Min Act: -0.0000

Data Index: 80557 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1844. Min Act: -0.0000

Data Index: 598096 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1893. Min Act: -0.0000

Data Index: 428074 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1883. Min Act: -0.0000

Data Index: 466561 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1812. Min Act: -0.0000

Data Index: 316067 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1763. Min Act: -0.0001

Data Index: 1213098 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1683. Min Act: -0.0000

Data Index: 549599 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1804. Min Act: -0.0000

Data Index: 985750 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1791. Min Act: -0.0000

Data Index: 475674 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1174619 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1785. Min Act: -0.0000

Data Index: 690360 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1717. Min Act: -0.0000

Data Index: 18406 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1743. Min Act: -0.0001

Data Index: 81218 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1748. Min Act: -0.0000

Data Index: 257593 (C4 (Web Text))

Max Activating Token Index: 116