Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2468 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.2472. Min Act: -0.0000

Data Index: 148263 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.2998. Min Act: -0.0000

Data Index: 989230 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.1299. Min Act: -0.0000

Data Index: 1233940 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.1796. Min Act: -0.0000

Data Index: 866972 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.0830. Min Act: -0.0000

Data Index: 220644 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.0712. Min Act: -0.0000

Data Index: 838598 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.1307. Min Act: -0.0000

Data Index: 405900 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.0553. Min Act: -0.0000

Data Index: 295103 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.0244. Min Act: -0.0000

Data Index: 6168 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.0501. Min Act: -0.0000

Data Index: 1121341 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.0414. Min Act: -0.0000

Data Index: 1086529 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.9509. Min Act: -0.0000

Data Index: 444426 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.0107. Min Act: -0.0000

Data Index: 614105 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.9755. Min Act: -0.0000

Data Index: 785382 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.9839. Min Act: -0.0000

Data Index: 500202 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.9529. Min Act: -0.0000

Data Index: 1212476 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.0072. Min Act: -0.0000

Data Index: 951469 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.9842. Min Act: -0.0000

Data Index: 532577 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1199048 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.9168. Min Act: -0.0000

Data Index: 969648 (C4 (Web Text))

Max Activating Token Index: 454