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

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

Neuron 2915 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.2818. Min Act: -0.0001

Data Index: 395450 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.3522. Min Act: -0.0001

Data Index: 278185 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.2234. Min Act: -0.0000

Data Index: 830990 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.1635. Min Act: -0.0001

Data Index: 473805 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.1513. Min Act: -0.0000

Data Index: 846023 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.1807. Min Act: -0.0001

Data Index: 490797 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.2357. Min Act: -0.0001

Data Index: 491552 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.1435. Min Act: -0.0000

Data Index: 779176 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0700. Min Act: -0.0000

Data Index: 1014586 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.1349. Min Act: -0.0001

Data Index: 1234462 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.1367. Min Act: -0.0001

Data Index: 817617 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.1880. Min Act: -0.0001

Data Index: 725973 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.1573. Min Act: -0.0001

Data Index: 1152439 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9840. Min Act: -0.0000

Data Index: 542388 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0048. Min Act: -0.0001

Data Index: 554539 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0843. Min Act: -0.0001

Data Index: 717986 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.1537. Min Act: -0.0001

Data Index: 694507 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9659. Min Act: -0.0000

Data Index: 550612 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0995. Min Act: -0.0000

Data Index: 848701 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0286. Min Act: -0.0001

Data Index: 1276285 (C4 (Web Text))

Max Activating Token Index: 1009