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

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

Neuron 494 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: 3.0916. Min Range: -3.0916

Max Act: 3.0916. Min Act: 0.0000

Data Index: 1426715 (Python Code)

Max Activating Token Index: 117

Text #1

Max Range: 3.0916. Min Range: -3.0916

Max Act: 2.6696. Min Act: 0.0001

Data Index: 1560415 (Python Code)

Max Activating Token Index: 206

Text #2

Max Range: 3.0916. Min Range: -3.0916

Max Act: 2.3827. Min Act: -0.0000

Data Index: 1425880 (Python Code)

Max Activating Token Index: 730

Text #3

Max Range: 3.0916. Min Range: -3.0916

Max Act: 2.2451. Min Act: 0.0001

Data Index: 1615405 (Python Code)

Max Activating Token Index: 292

Text #4

Max Range: 3.0916. Min Range: -3.0916

Max Act: 1.8273. Min Act: -0.0000

Data Index: 182587 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 3.0916. Min Range: -3.0916

Max Act: 1.5279. Min Act: -0.0000

Data Index: 1559699 (Python Code)

Max Activating Token Index: 278

Text #6

Max Range: 3.0916. Min Range: -3.0916

Max Act: 1.6937. Min Act: 0.0000

Data Index: 1614535 (Python Code)

Max Activating Token Index: 110

Text #7

Max Range: 3.0916. Min Range: -3.0916

Max Act: 1.8119. Min Act: 0.0001

Data Index: 1591467 (Python Code)

Max Activating Token Index: 332

Text #8

Max Range: 3.0916. Min Range: -3.0916

Max Act: 1.5631. Min Act: -0.0000

Data Index: 680975 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 3.0916. Min Range: -3.0916

Max Act: 1.7226. Min Act: -0.0000

Data Index: 1435310 (Python Code)

Max Activating Token Index: 260

Text #10

Max Range: 3.0916. Min Range: -3.0916

Max Act: 1.6851. Min Act: 0.0001

Data Index: 1639255 (Python Code)

Max Activating Token Index: 738

Text #11

Max Range: 3.0916. Min Range: -3.0916

Max Act: 1.7439. Min Act: 0.0000

Data Index: 1394299 (Python Code)

Max Activating Token Index: 180

Text #12

Max Range: 3.0916. Min Range: -3.0916

Max Act: 1.6181. Min Act: 0.0001

Data Index: 1489466 (Python Code)

Max Activating Token Index: 662

Text #13

Max Range: 3.0916. Min Range: -3.0916

Max Act: 1.5660. Min Act: -0.0000

Data Index: 771912 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 3.0916. Min Range: -3.0916

Max Act: 1.5089. Min Act: -0.0000

Data Index: 1458403 (Python Code)

Max Activating Token Index: 250

Text #15

Max Range: 3.0916. Min Range: -3.0916

Max Act: 1.5245. Min Act: -0.0000

Data Index: 48609 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 3.0916. Min Range: -3.0916

Max Act: 1.6693. Min Act: -0.0000

Data Index: 144163 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 3.0916. Min Range: -3.0916

Max Act: 1.3987. Min Act: -0.0000

Data Index: 1568373 (Python Code)

Max Activating Token Index: 191

Text #18

Max Range: 3.0916. Min Range: -3.0916

Max Act: 1.3418. Min Act: 0.0000

Data Index: 1369734 (Python Code)

Max Activating Token Index: 138

Text #19

Max Range: 3.0916. Min Range: -3.0916

Max Act: 1.3813. Min Act: 0.0000

Data Index: 1606387 (Python Code)

Max Activating Token Index: 933