Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 681 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.1846. Min Act: -0.0000

Data Index: 984672 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.1144. Min Act: -0.0000

Data Index: 282930 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0620. Min Act: -0.0000

Data Index: 473791 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1090976 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0079. Min Act: -0.0000

Data Index: 720469 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0005. Min Act: -0.0000

Data Index: 1305266 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0399. Min Act: -0.0000

Data Index: 126504 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0026. Min Act: -0.0000

Data Index: 1159725 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.7262. Min Act: -0.0000

Data Index: 37730 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.9665. Min Act: -0.0000

Data Index: 399074 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.9363. Min Act: -0.0000

Data Index: 844865 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.8772. Min Act: -0.0000

Data Index: 1194160 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.8659. Min Act: -0.0000

Data Index: 326132 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.9232. Min Act: -0.0001

Data Index: 967649 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.9199. Min Act: -0.0000

Data Index: 986698 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.8690. Min Act: -0.0000

Data Index: 701506 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0043. Min Act: -0.0001

Data Index: 1036239 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.8992. Min Act: -0.0000

Data Index: 879328 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.9006. Min Act: -0.0000

Data Index: 58664 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.8805. Min Act: -0.0000

Data Index: 205246 (C4 (Web Text))

Max Activating Token Index: 528