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

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

Neuron 2515 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: 1.9273. Min Range: -1.9273

Max Act: 1.9273. Min Act: -0.0000

Data Index: 1570982 (Python Code)

Max Activating Token Index: 117

Text #1

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.8105. Min Act: -0.0000

Data Index: 1645325 (Python Code)

Max Activating Token Index: 730

Text #2

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.7882. Min Act: -0.0000

Data Index: 1627900 (Python Code)

Max Activating Token Index: 108

Text #3

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.7032. Min Act: -0.0000

Data Index: 1535715 (Python Code)

Max Activating Token Index: 919

Text #4

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.8317. Min Act: -0.0000

Data Index: 1405229 (Python Code)

Max Activating Token Index: 128

Text #5

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.7995. Min Act: -0.0000

Data Index: 1560370 (Python Code)

Max Activating Token Index: 162

Text #6

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.7467. Min Act: -0.0000

Data Index: 1651382 (Python Code)

Max Activating Token Index: 346

Text #7

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.6460. Min Act: -0.0000

Data Index: 1520340 (Python Code)

Max Activating Token Index: 918

Text #8

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.6788. Min Act: -0.0000

Data Index: 1654073 (Python Code)

Max Activating Token Index: 926

Text #9

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.5866. Min Act: -0.0000

Data Index: 1471365 (Python Code)

Max Activating Token Index: 145

Text #10

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.4994. Min Act: -0.0000

Data Index: 1619830 (Python Code)

Max Activating Token Index: 142

Text #11

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.5535. Min Act: -0.0000

Data Index: 1572799 (Python Code)

Max Activating Token Index: 434

Text #12

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.5769. Min Act: -0.0000

Data Index: 1480979 (Python Code)

Max Activating Token Index: 293

Text #13

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.5649. Min Act: -0.0000

Data Index: 1536169 (Python Code)

Max Activating Token Index: 993

Text #14

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.4592. Min Act: -0.0000

Data Index: 1504913 (Python Code)

Max Activating Token Index: 785

Text #15

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.4408. Min Act: -0.0000

Data Index: 1508998 (Python Code)

Max Activating Token Index: 752

Text #16

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.4805. Min Act: -0.0000

Data Index: 1639614 (Python Code)

Max Activating Token Index: 159

Text #17

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.4162. Min Act: -0.0000

Data Index: 1516334 (Python Code)

Max Activating Token Index: 452

Text #18

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.4670. Min Act: -0.0000

Data Index: 1400900 (Python Code)

Max Activating Token Index: 342

Text #19

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.3946. Min Act: -0.0000

Data Index: 1423016 (Python Code)

Max Activating Token Index: 171