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

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

Neuron 6066 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6376. Min Range: -2.6376

Max Act: 2.6376. Min Act: -0.0000

Data Index: 804443 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 2.6376. Min Range: -2.6376

Max Act: 2.2350. Min Act: -0.0000

Data Index: 250894 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 2.6376. Min Range: -2.6376

Max Act: 1.9996. Min Act: -0.0000

Data Index: 420150 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 2.6376. Min Range: -2.6376

Max Act: 2.1481. Min Act: -0.0000

Data Index: 116898 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 2.6376. Min Range: -2.6376

Max Act: 2.0170. Min Act: -0.0000

Data Index: 1293458 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 2.6376. Min Range: -2.6376

Max Act: 1.2156. Min Act: -0.0000

Data Index: 579681 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 2.6376. Min Range: -2.6376

Max Act: 1.3125. Min Act: -0.0000

Data Index: 159169 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 2.6376. Min Range: -2.6376

Max Act: 1.5193. Min Act: -0.0000

Data Index: 58066 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 2.6376. Min Range: -2.6376

Max Act: 1.1760. Min Act: -0.0000

Data Index: 609031 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 2.6376. Min Range: -2.6376

Max Act: 1.1433. Min Act: 0.0000

Data Index: 579548 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 2.6376. Min Range: -2.6376

Max Act: 0.9333. Min Act: -0.0000

Data Index: 403858 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 2.6376. Min Range: -2.6376

Max Act: 1.1546. Min Act: -0.0000

Data Index: 437642 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 2.6376. Min Range: -2.6376

Max Act: 1.0199. Min Act: -0.0000

Data Index: 354679 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 2.6376. Min Range: -2.6376

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1576281 (Python Code)

Max Activating Token Index: 745

Text #14

Max Range: 2.6376. Min Range: -2.6376

Max Act: 0.8788. Min Act: -0.0000

Data Index: 1583131 (Python Code)

Max Activating Token Index: 647

Text #15

Max Range: 2.6376. Min Range: -2.6376

Max Act: 1.0281. Min Act: -0.0000

Data Index: 1359973 (Python Code)

Max Activating Token Index: 636

Text #16

Max Range: 2.6376. Min Range: -2.6376

Max Act: 0.9222. Min Act: 0.0001

Data Index: 822274 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 2.6376. Min Range: -2.6376

Max Act: 0.9651. Min Act: -0.0000

Data Index: 537353 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 2.6376. Min Range: -2.6376

Max Act: 1.1305. Min Act: -0.0000

Data Index: 1599959 (Python Code)

Max Activating Token Index: 248

Text #19

Max Range: 2.6376. Min Range: -2.6376

Max Act: 0.8823. Min Act: 0.0001

Data Index: 1435305 (Python Code)

Max Activating Token Index: 995