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

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

Neuron 3939 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1023. Min Range: -2.1023

Max Act: 2.1023. Min Act: -0.0000

Data Index: 808978 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.9461. Min Act: -0.0000

Data Index: 562532 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.9424. Min Act: -0.0000

Data Index: 1244689 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.7159. Min Act: -0.0000

Data Index: 482625 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.4751. Min Act: -0.0000

Data Index: 458901 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.4538. Min Act: -0.0000

Data Index: 1268885 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.3947. Min Act: -0.0000

Data Index: 245252 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.3624. Min Act: -0.0000

Data Index: 1095515 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.4320. Min Act: -0.0000

Data Index: 955966 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.2846. Min Act: -0.0000

Data Index: 1319465 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.2932. Min Act: -0.0000

Data Index: 787048 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.2903. Min Act: -0.0000

Data Index: 544919 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.3171. Min Act: -0.0000

Data Index: 976805 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.3935. Min Act: -0.0000

Data Index: 1246070 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.3785. Min Act: -0.0000

Data Index: 523836 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.3798. Min Act: -0.0000

Data Index: 92468 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.2563. Min Act: -0.0000

Data Index: 904373 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.1921. Min Act: -0.0000

Data Index: 578217 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.1522. Min Act: -0.0000

Data Index: 919879 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 2.1023. Min Range: -2.1023

Max Act: 1.2114. Min Act: -0.0000

Data Index: 506938 (C4 (Web Text))

Max Activating Token Index: 52