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

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

Neuron 2975 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2692. Min Act: -0.0001

Data Index: 449688 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2647. Min Act: -0.0001

Data Index: 1061874 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2635. Min Act: -0.0000

Data Index: 562883 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2478. Min Act: -0.0001

Data Index: 507047 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2235. Min Act: -0.0000

Data Index: 194570 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1233026 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2011. Min Act: -0.0000

Data Index: 77788 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1963. Min Act: -0.0001

Data Index: 1187809 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1947. Min Act: -0.0001

Data Index: 544950 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1998. Min Act: -0.0001

Data Index: 984978 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1970. Min Act: -0.0001

Data Index: 1233095 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1959. Min Act: -0.0001

Data Index: 1324000 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1942. Min Act: -0.0001

Data Index: 180680 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1917. Min Act: -0.0001

Data Index: 643902 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1782. Min Act: -0.0001

Data Index: 851441 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1827. Min Act: -0.0000

Data Index: 1276013 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1872. Min Act: -0.0001

Data Index: 1152450 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1864. Min Act: -0.0001

Data Index: 331000 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1742. Min Act: -0.0000

Data Index: 653762 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1858. Min Act: -0.0000

Data Index: 906784 (C4 (Web Text))

Max Activating Token Index: 752