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

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

Neuron 1706 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1175. Min Range: -1.1175

Max Act: 1.1175. Min Act: -0.0000

Data Index: 1014577 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.7294. Min Act: -0.0000

Data Index: 467174 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.6478. Min Act: -0.0000

Data Index: 598693 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.7161. Min Act: -0.0000

Data Index: 130866 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.7052. Min Act: -0.0000

Data Index: 710907 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.6711. Min Act: -0.0000

Data Index: 511124 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.6612. Min Act: -0.0000

Data Index: 516675 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.6555. Min Act: -0.0000

Data Index: 940812 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.6266. Min Act: -0.0000

Data Index: 1196474 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1228790 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.6201. Min Act: -0.0000

Data Index: 180314 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.5367. Min Act: -0.0000

Data Index: 838618 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1009960 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.6045. Min Act: -0.0000

Data Index: 674708 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.5849. Min Act: 0.0000

Data Index: 816671 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.5975. Min Act: -0.0000

Data Index: 274274 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.5865. Min Act: -0.0000

Data Index: 674349 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.5600. Min Act: -0.0000

Data Index: 40155 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.5487. Min Act: -0.0000

Data Index: 56331 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 1.1175. Min Range: -1.1175

Max Act: 0.5408. Min Act: -0.0000

Data Index: 174606 (C4 (Web Text))

Max Activating Token Index: 169