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

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

Neuron 2008 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.9884. Min Act: -0.0000

Data Index: 301654 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.2340. Min Act: -0.0000

Data Index: 637764 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.1746. Min Act: -0.0000

Data Index: 38727 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.8081. Min Act: -0.0000

Data Index: 4598 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.9354. Min Act: -0.0000

Data Index: 1187123 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.7756. Min Act: -0.0000

Data Index: 472860 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.9026. Min Act: -0.0000

Data Index: 550345 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.7422. Min Act: -0.0000

Data Index: 1030884 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.8643. Min Act: -0.0000

Data Index: 1209628 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.7155. Min Act: -0.0000

Data Index: 41635 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.7199. Min Act: -0.0000

Data Index: 751677 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.5271. Min Act: -0.0000

Data Index: 63951 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.7985. Min Act: -0.0000

Data Index: 549655 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.6334. Min Act: -0.0000

Data Index: 520891 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.5057. Min Act: -0.0000

Data Index: 969787 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.6077. Min Act: -0.0000

Data Index: 663518 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.6221. Min Act: -0.0000

Data Index: 140570 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.5467. Min Act: -0.0000

Data Index: 1313175 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.6373. Min Act: -0.0000

Data Index: 731641 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.6228. Min Act: -0.0000

Data Index: 971010 (C4 (Web Text))

Max Activating Token Index: 111