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

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

Neuron 344 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.9006. Min Act: -0.0000

Data Index: 672714 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.7784. Min Act: -0.0000

Data Index: 131458 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.5859. Min Act: -0.0000

Data Index: 878237 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.9930. Min Act: -0.0000

Data Index: 1290086 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.7560. Min Act: -0.0001

Data Index: 1002777 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.7568. Min Act: -0.0000

Data Index: 900750 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.6949. Min Act: -0.0000

Data Index: 705052 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.6783. Min Act: -0.0001

Data Index: 1257117 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.6925. Min Act: -0.0000

Data Index: 692534 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.6744. Min Act: -0.0000

Data Index: 1095366 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.6318. Min Act: -0.0000

Data Index: 177369 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.5067. Min Act: -0.0000

Data Index: 1162402 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.4948. Min Act: -0.0000

Data Index: 1124597 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.5700. Min Act: -0.0000

Data Index: 861062 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.5652. Min Act: -0.0000

Data Index: 131846 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.5494. Min Act: -0.0000

Data Index: 827679 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.4559. Min Act: -0.0000

Data Index: 859549 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.5302. Min Act: -0.0000

Data Index: 649691 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.4905. Min Act: -0.0001

Data Index: 69281 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.4012. Min Act: -0.0000

Data Index: 1162556 (C4 (Web Text))

Max Activating Token Index: 12