Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2003 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4770. Min Act: -0.0001

Data Index: 1201544 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4629. Min Act: -0.0001

Data Index: 320814 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4594. Min Act: -0.0001

Data Index: 139341 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4209. Min Act: -0.0001

Data Index: 817647 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4301. Min Act: -0.0001

Data Index: 257963 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4133. Min Act: -0.0001

Data Index: 1328799 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3917. Min Act: -0.0001

Data Index: 889596 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4004. Min Act: -0.0001

Data Index: 836366 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3834. Min Act: -0.0001

Data Index: 207944 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3711. Min Act: -0.0001

Data Index: 1225907 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3634. Min Act: -0.0001

Data Index: 156007 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3746. Min Act: -0.0001

Data Index: 326319 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3805. Min Act: -0.0001

Data Index: 1352964 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3425. Min Act: -0.0001

Data Index: 206880 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3538. Min Act: -0.0001

Data Index: 384215 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3897. Min Act: -0.0001

Data Index: 891130 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3470. Min Act: -0.0001

Data Index: 1068664 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3588. Min Act: -0.0001

Data Index: 388727 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3454. Min Act: -0.0001

Data Index: 1050763 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3433. Min Act: -0.0001

Data Index: 1240133 (C4 (Web Text))

Max Activating Token Index: 873