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

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

Neuron 1993 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.9318. Min Act: 0.0000

Data Index: 1023156 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.7326. Min Act: -0.0000

Data Index: 174628 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.7032. Min Act: -0.0000

Data Index: 1117441 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.5569. Min Act: -0.0000

Data Index: 393023 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.5363. Min Act: 0.0001

Data Index: 321968 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.6586. Min Act: -0.0000

Data Index: 475510 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.3642. Min Act: -0.0000

Data Index: 376768 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.1596. Min Act: -0.0000

Data Index: 399345 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.2706. Min Act: -0.0000

Data Index: 939949 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.3612. Min Act: -0.0000

Data Index: 869680 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.2487. Min Act: 0.0000

Data Index: 32742 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.2245. Min Act: 0.0000

Data Index: 370790 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.2217. Min Act: -0.0000

Data Index: 459181 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.1947. Min Act: -0.0000

Data Index: 332525 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.1796. Min Act: -0.0000

Data Index: 1246212 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.0506. Min Act: -0.0000

Data Index: 1232548 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.1540. Min Act: 0.0000

Data Index: 548090 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.1281. Min Act: -0.0000

Data Index: 274910 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.1557. Min Act: -0.0000

Data Index: 558161 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 2.9318. Min Range: -2.9318

Max Act: 2.1194. Min Act: 0.0001

Data Index: 1099347 (C4 (Web Text))

Max Activating Token Index: 519