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

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

Neuron 767 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3103. Min Range: -1.3103

Max Act: 1.3103. Min Act: -0.0001

Data Index: 988487 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.8796. Min Act: -0.0001

Data Index: 128038 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.9476. Min Act: -0.0001

Data Index: 1150865 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.8904. Min Act: -0.0001

Data Index: 266150 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.8898. Min Act: -0.0001

Data Index: 1320121 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.8857. Min Act: -0.0001

Data Index: 770864 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.7983. Min Act: -0.0001

Data Index: 34844 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.8828. Min Act: -0.0001

Data Index: 694379 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.8462. Min Act: -0.0001

Data Index: 243685 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.8301. Min Act: -0.0001

Data Index: 718048 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.8425. Min Act: -0.0001

Data Index: 866015 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.7895. Min Act: -0.0001

Data Index: 531692 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.7692. Min Act: -0.0001

Data Index: 1286647 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.8572. Min Act: -0.0001

Data Index: 8634 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.7143. Min Act: -0.0001

Data Index: 306394 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.7317. Min Act: -0.0001

Data Index: 428473 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.6879. Min Act: -0.0001

Data Index: 613883 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.7805. Min Act: -0.0001

Data Index: 995845 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.7247. Min Act: -0.0001

Data Index: 302579 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 1.3103. Min Range: -1.3103

Max Act: 0.7422. Min Act: -0.0001

Data Index: 771451 (C4 (Web Text))

Max Activating Token Index: 842