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

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

Neuron 2798 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: 0.2840. Min Range: -0.2840

Max Act: 0.2746. Min Act: -0.0001

Data Index: 1104758 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2830. Min Act: -0.0001

Data Index: 682868 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2733. Min Act: -0.0001

Data Index: 399549 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2840. Min Act: -0.0001

Data Index: 187628 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2568. Min Act: -0.0001

Data Index: 250547 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2449. Min Act: -0.0001

Data Index: 851757 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2426. Min Act: -0.0001

Data Index: 1010991 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2436. Min Act: -0.0001

Data Index: 190540 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2262. Min Act: -0.0001

Data Index: 1052942 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2265. Min Act: -0.0001

Data Index: 121807 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2342. Min Act: -0.0001

Data Index: 116104 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2332. Min Act: -0.0001

Data Index: 871608 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2327. Min Act: -0.0001

Data Index: 149518 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2387. Min Act: -0.0001

Data Index: 364009 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2292. Min Act: -0.0001

Data Index: 229978 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2353. Min Act: -0.0001

Data Index: 157629 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2493. Min Act: -0.0001

Data Index: 71954 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2481. Min Act: -0.0001

Data Index: 326062 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2113. Min Act: -0.0001

Data Index: 149155 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2408. Min Act: -0.0001

Data Index: 1233908 (C4 (Web Text))

Max Activating Token Index: 545