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

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

Neuron 1058 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7826. Min Range: -1.7826

Max Act: 1.7826. Min Act: -0.0000

Data Index: 1180871 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 1.7826. Min Range: -1.7826

Max Act: 1.6863. Min Act: -0.0000

Data Index: 308033 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 1.7826. Min Range: -1.7826

Max Act: 1.7593. Min Act: -0.0000

Data Index: 224164 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 1.7826. Min Range: -1.7826

Max Act: 1.4442. Min Act: 0.0000

Data Index: 935567 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 1.7826. Min Range: -1.7826

Max Act: 1.2911. Min Act: -0.0000

Data Index: 1060337 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 1.7826. Min Range: -1.7826

Max Act: 1.2774. Min Act: -0.0000

Data Index: 994097 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 1.7826. Min Range: -1.7826

Max Act: 1.1886. Min Act: -0.0000

Data Index: 469397 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 1.7826. Min Range: -1.7826

Max Act: 1.2430. Min Act: -0.0000

Data Index: 1335139 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 1.7826. Min Range: -1.7826

Max Act: 1.2568. Min Act: -0.0000

Data Index: 1284253 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 1.7826. Min Range: -1.7826

Max Act: 1.2827. Min Act: -0.0000

Data Index: 812024 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 1.7826. Min Range: -1.7826

Max Act: 1.1965. Min Act: -0.0000

Data Index: 105622 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 1.7826. Min Range: -1.7826

Max Act: 1.0866. Min Act: 0.0000

Data Index: 543387 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 1.7826. Min Range: -1.7826

Max Act: 0.9721. Min Act: -0.0000

Data Index: 318570 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 1.7826. Min Range: -1.7826

Max Act: 1.1769. Min Act: -0.0000

Data Index: 454989 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 1.7826. Min Range: -1.7826

Max Act: 1.1260. Min Act: -0.0000

Data Index: 289706 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 1.7826. Min Range: -1.7826

Max Act: 1.0992. Min Act: -0.0000

Data Index: 736118 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 1.7826. Min Range: -1.7826

Max Act: 1.0367. Min Act: -0.0000

Data Index: 298905 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 1.7826. Min Range: -1.7826

Max Act: 1.0479. Min Act: -0.0000

Data Index: 304695 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 1.7826. Min Range: -1.7826

Max Act: 1.0028. Min Act: -0.0000

Data Index: 522989 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 1.7826. Min Range: -1.7826

Max Act: 0.9839. Min Act: -0.0000

Data Index: 670166 (C4 (Web Text))

Max Activating Token Index: 921