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

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

Neuron 3063 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: 0.0637. Min Range: -0.0637

Max Act: 0.0637. Min Act: -0.0001

Data Index: 1147384 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0542. Min Act: -0.0001

Data Index: 1328118 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0473. Min Act: -0.0000

Data Index: 1203378 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0492. Min Act: -0.0000

Data Index: 568321 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0492. Min Act: -0.0001

Data Index: 1059174 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0486. Min Act: -0.0001

Data Index: 52863 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0447. Min Act: -0.0001

Data Index: 761050 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0448. Min Act: -0.0000

Data Index: 668947 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0463. Min Act: -0.0001

Data Index: 395868 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0431. Min Act: -0.0000

Data Index: 524145 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0445. Min Act: -0.0001

Data Index: 461148 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0425. Min Act: -0.0000

Data Index: 1120603 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0455. Min Act: -0.0000

Data Index: 839791 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0409. Min Act: -0.0001

Data Index: 695748 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0404. Min Act: -0.0000

Data Index: 609240 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0432. Min Act: -0.0001

Data Index: 177427 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0425. Min Act: -0.0001

Data Index: 600544 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0382. Min Act: -0.0001

Data Index: 716362 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0422. Min Act: -0.0001

Data Index: 1519993 (Python Code)

Max Activating Token Index: 709

Text #19

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0404. Min Act: -0.0000

Data Index: 1322932 (C4 (Web Text))

Max Activating Token Index: 444