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

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

Neuron 3046 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: 1.3298. Min Range: -1.3298

Max Act: 1.3298. Min Act: -0.0001

Data Index: 649763 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.1831. Min Act: -0.0001

Data Index: 1264249 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.1335. Min Act: -0.0001

Data Index: 707024 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.0026. Min Act: -0.0001

Data Index: 824827 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.9571. Min Act: -0.0001

Data Index: 1064821 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.9157. Min Act: -0.0001

Data Index: 779739 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.8724. Min Act: -0.0001

Data Index: 1310670 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.8946. Min Act: -0.0001

Data Index: 60921 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.8351. Min Act: -0.0001

Data Index: 1158484 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.7795. Min Act: -0.0001

Data Index: 1256402 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.8110. Min Act: -0.0001

Data Index: 1135651 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.7833. Min Act: -0.0001

Data Index: 591035 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.7698. Min Act: -0.0001

Data Index: 963310 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.8131. Min Act: -0.0001

Data Index: 1071597 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.7505. Min Act: -0.0001

Data Index: 888412 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.7492. Min Act: -0.0001

Data Index: 248949 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.7424. Min Act: -0.0001

Data Index: 1305358 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.7735. Min Act: -0.0001

Data Index: 280036 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.6981. Min Act: -0.0001

Data Index: 963955 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.7473. Min Act: -0.0001

Data Index: 576734 (C4 (Web Text))

Max Activating Token Index: 654