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

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

Neuron 606 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: 0.3961. Min Range: -0.3961

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1189503 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1280190 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2873. Min Act: -0.0000

Data Index: 325798 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2911. Min Act: -0.0000

Data Index: 367224 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2772. Min Act: -0.0001

Data Index: 1197931 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2552. Min Act: -0.0000

Data Index: 187949 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2698. Min Act: -0.0000

Data Index: 1166031 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2794. Min Act: -0.0000

Data Index: 1257590 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2557. Min Act: -0.0000

Data Index: 23306 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2634. Min Act: -0.0000

Data Index: 607879 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2246. Min Act: -0.0000

Data Index: 405625 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2406. Min Act: -0.0000

Data Index: 35884 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2288. Min Act: -0.0000

Data Index: 590766 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2162. Min Act: -0.0000

Data Index: 970056 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1199519 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2237. Min Act: -0.0000

Data Index: 795422 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1123190 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2259. Min Act: -0.0000

Data Index: 723802 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.1962. Min Act: -0.0000

Data Index: 308595 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1209594 (C4 (Web Text))

Max Activating Token Index: 17