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

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

Neuron 3667 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: 5.0786. Min Range: -5.0786

Max Act: 5.0786. Min Act: -0.0000

Data Index: 1479533 (Python Code)

Max Activating Token Index: 531

Text #1

Max Range: 5.0786. Min Range: -5.0786

Max Act: 4.9307. Min Act: -0.0000

Data Index: 1484753 (Python Code)

Max Activating Token Index: 157

Text #2

Max Range: 5.0786. Min Range: -5.0786

Max Act: 4.7151. Min Act: -0.0000

Data Index: 1433489 (Python Code)

Max Activating Token Index: 392

Text #3

Max Range: 5.0786. Min Range: -5.0786

Max Act: 4.7851. Min Act: -0.0000

Data Index: 1478485 (Python Code)

Max Activating Token Index: 323

Text #4

Max Range: 5.0786. Min Range: -5.0786

Max Act: 4.7716. Min Act: -0.0000

Data Index: 1487683 (Python Code)

Max Activating Token Index: 277

Text #5

Max Range: 5.0786. Min Range: -5.0786

Max Act: 4.5755. Min Act: -0.0000

Data Index: 1652919 (Python Code)

Max Activating Token Index: 184

Text #6

Max Range: 5.0786. Min Range: -5.0786

Max Act: 4.7133. Min Act: -0.0000

Data Index: 1553620 (Python Code)

Max Activating Token Index: 359

Text #7

Max Range: 5.0786. Min Range: -5.0786

Max Act: 4.7052. Min Act: -0.0000

Data Index: 1631231 (Python Code)

Max Activating Token Index: 645

Text #8

Max Range: 5.0786. Min Range: -5.0786

Max Act: 5.0194. Min Act: -0.0000

Data Index: 1370327 (Python Code)

Max Activating Token Index: 232

Text #9

Max Range: 5.0786. Min Range: -5.0786

Max Act: 4.5938. Min Act: -0.0000

Data Index: 1523952 (Python Code)

Max Activating Token Index: 109

Text #10

Max Range: 5.0786. Min Range: -5.0786

Max Act: 4.5648. Min Act: -0.0000

Data Index: 1595733 (Python Code)

Max Activating Token Index: 332

Text #11

Max Range: 5.0786. Min Range: -5.0786

Max Act: 4.3927. Min Act: -0.0000

Data Index: 1420905 (Python Code)

Max Activating Token Index: 655

Text #12

Max Range: 5.0786. Min Range: -5.0786

Max Act: 4.4023. Min Act: -0.0000

Data Index: 1624305 (Python Code)

Max Activating Token Index: 594

Text #13

Max Range: 5.0786. Min Range: -5.0786

Max Act: 4.4088. Min Act: -0.0000

Data Index: 1400856 (Python Code)

Max Activating Token Index: 5

Text #14

Max Range: 5.0786. Min Range: -5.0786

Max Act: 4.3640. Min Act: -0.0000

Data Index: 1541564 (Python Code)

Max Activating Token Index: 924

Text #15

Max Range: 5.0786. Min Range: -5.0786

Max Act: 4.2212. Min Act: -0.0000

Data Index: 1435119 (Python Code)

Max Activating Token Index: 125

Text #16

Max Range: 5.0786. Min Range: -5.0786

Max Act: 4.1673. Min Act: -0.0000

Data Index: 1383968 (Python Code)

Max Activating Token Index: 174

Text #17

Max Range: 5.0786. Min Range: -5.0786

Max Act: 4.1096. Min Act: -0.0000

Data Index: 1458104 (Python Code)

Max Activating Token Index: 770

Text #18

Max Range: 5.0786. Min Range: -5.0786

Max Act: 4.1483. Min Act: -0.0000

Data Index: 1583341 (Python Code)

Max Activating Token Index: 540

Text #19

Max Range: 5.0786. Min Range: -5.0786

Max Act: 4.2853. Min Act: -0.0000

Data Index: 1373776 (Python Code)

Max Activating Token Index: 80