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

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

Neuron 2828 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3756. Min Range: -2.3756

Max Act: 2.3756. Min Act: -0.0000

Data Index: 1374884 (Python Code)

Max Activating Token Index: 280

Text #1

Max Range: 2.3756. Min Range: -2.3756

Max Act: 1.8851. Min Act: -0.0000

Data Index: 1592950 (Python Code)

Max Activating Token Index: 175

Text #2

Max Range: 2.3756. Min Range: -2.3756

Max Act: 1.7692. Min Act: -0.0000

Data Index: 1529116 (Python Code)

Max Activating Token Index: 312

Text #3

Max Range: 2.3756. Min Range: -2.3756

Max Act: 1.9473. Min Act: -0.0000

Data Index: 1439592 (Python Code)

Max Activating Token Index: 887

Text #4

Max Range: 2.3756. Min Range: -2.3756

Max Act: 2.0321. Min Act: -0.0000

Data Index: 1625662 (Python Code)

Max Activating Token Index: 281

Text #5

Max Range: 2.3756. Min Range: -2.3756

Max Act: 1.9232. Min Act: -0.0001

Data Index: 1461590 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 2.3756. Min Range: -2.3756

Max Act: 1.8891. Min Act: -0.0000

Data Index: 1546160 (Python Code)

Max Activating Token Index: 144

Text #7

Max Range: 2.3756. Min Range: -2.3756

Max Act: 1.8272. Min Act: -0.0000

Data Index: 1479776 (Python Code)

Max Activating Token Index: 403

Text #8

Max Range: 2.3756. Min Range: -2.3756

Max Act: 1.8715. Min Act: -0.0000

Data Index: 1636004 (Python Code)

Max Activating Token Index: 262

Text #9

Max Range: 2.3756. Min Range: -2.3756

Max Act: 1.8761. Min Act: -0.0001

Data Index: 1446536 (Python Code)

Max Activating Token Index: 106

Text #10

Max Range: 2.3756. Min Range: -2.3756

Max Act: 1.8651. Min Act: -0.0001

Data Index: 1450134 (Python Code)

Max Activating Token Index: 170

Text #11

Max Range: 2.3756. Min Range: -2.3756

Max Act: 1.8617. Min Act: -0.0000

Data Index: 1481572 (Python Code)

Max Activating Token Index: 368

Text #12

Max Range: 2.3756. Min Range: -2.3756

Max Act: 1.9334. Min Act: -0.0001

Data Index: 1633892 (Python Code)

Max Activating Token Index: 309

Text #13

Max Range: 2.3756. Min Range: -2.3756

Max Act: 1.8411. Min Act: -0.0000

Data Index: 1403269 (Python Code)

Max Activating Token Index: 811

Text #14

Max Range: 2.3756. Min Range: -2.3756

Max Act: 1.8349. Min Act: -0.0000

Data Index: 1545588 (Python Code)

Max Activating Token Index: 641

Text #15

Max Range: 2.3756. Min Range: -2.3756

Max Act: 1.7433. Min Act: -0.0000

Data Index: 1394061 (Python Code)

Max Activating Token Index: 183

Text #16

Max Range: 2.3756. Min Range: -2.3756

Max Act: 1.7407. Min Act: -0.0000

Data Index: 1501916 (Python Code)

Max Activating Token Index: 674

Text #17

Max Range: 2.3756. Min Range: -2.3756

Max Act: 1.7211. Min Act: -0.0000

Data Index: 1505469 (Python Code)

Max Activating Token Index: 351

Text #18

Max Range: 2.3756. Min Range: -2.3756

Max Act: 1.6667. Min Act: -0.0001

Data Index: 1567607 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 2.3756. Min Range: -2.3756

Max Act: 1.6971. Min Act: -0.0000

Data Index: 1373912 (Python Code)

Max Activating Token Index: 323