Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1039 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.4324. Min Act: -0.0000

Data Index: 1015638 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.4154. Min Act: -0.0000

Data Index: 793095 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.3779. Min Act: -0.0001

Data Index: 1126241 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.3080. Min Act: -0.0000

Data Index: 1220860 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.1040. Min Act: -0.0000

Data Index: 1157781 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.2234. Min Act: -0.0000

Data Index: 821345 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.1350. Min Act: -0.0000

Data Index: 624304 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.1333. Min Act: -0.0000

Data Index: 724837 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0353. Min Act: -0.0000

Data Index: 685453 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0215. Min Act: -0.0000

Data Index: 263623 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0437. Min Act: -0.0000

Data Index: 1146153 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 1.4324. Min Range: -1.4324

Max Act: 0.9366. Min Act: -0.0000

Data Index: 472475 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0557. Min Act: -0.0000

Data Index: 830859 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.1135. Min Act: -0.0000

Data Index: 628472 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0706. Min Act: -0.0000

Data Index: 1031468 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0018. Min Act: -0.0000

Data Index: 653694 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0535. Min Act: -0.0000

Data Index: 397305 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.1082. Min Act: -0.0000

Data Index: 545739 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0287. Min Act: -0.0000

Data Index: 754916 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0177. Min Act: -0.0000

Data Index: 802727 (C4 (Web Text))

Max Activating Token Index: 233