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

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

Neuron 2136 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.6317. Min Act: -0.0000

Data Index: 152977 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.4512. Min Act: -0.0000

Data Index: 711448 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 4.6317. Min Range: -4.6317

Max Act: 3.9255. Min Act: -0.0000

Data Index: 1585554 (Python Code)

Max Activating Token Index: 874

Text #3

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.0563. Min Act: -0.0000

Data Index: 36201 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 4.6317. Min Range: -4.6317

Max Act: 3.8577. Min Act: -0.0000

Data Index: 736721 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 4.6317. Min Range: -4.6317

Max Act: 3.7438. Min Act: -0.0000

Data Index: 82478 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 4.6317. Min Range: -4.6317

Max Act: 3.7806. Min Act: -0.0000

Data Index: 180746 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 4.6317. Min Range: -4.6317

Max Act: 3.7024. Min Act: -0.0000

Data Index: 287669 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 4.6317. Min Range: -4.6317

Max Act: 3.4881. Min Act: -0.0000

Data Index: 576838 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 4.6317. Min Range: -4.6317

Max Act: 3.8395. Min Act: -0.0000

Data Index: 1291172 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 4.6317. Min Range: -4.6317

Max Act: 3.6800. Min Act: -0.0000

Data Index: 542663 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 4.6317. Min Range: -4.6317

Max Act: 3.6687. Min Act: -0.0000

Data Index: 684066 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 4.6317. Min Range: -4.6317

Max Act: 3.6232. Min Act: -0.0000

Data Index: 716613 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 4.6317. Min Range: -4.6317

Max Act: 3.4314. Min Act: -0.0000

Data Index: 1290706 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 4.6317. Min Range: -4.6317

Max Act: 3.4265. Min Act: -0.0000

Data Index: 154789 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 4.6317. Min Range: -4.6317

Max Act: 3.5695. Min Act: -0.0000

Data Index: 582785 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 4.6317. Min Range: -4.6317

Max Act: 3.5907. Min Act: -0.0000

Data Index: 167753 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 4.6317. Min Range: -4.6317

Max Act: 3.5837. Min Act: -0.0000

Data Index: 1272610 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 4.6317. Min Range: -4.6317

Max Act: 3.5849. Min Act: -0.0000

Data Index: 591369 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 4.6317. Min Range: -4.6317

Max Act: 3.5553. Min Act: -0.0000

Data Index: 385056 (C4 (Web Text))

Max Activating Token Index: 656