Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4545 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1553627 (Python Code)

Max Activating Token Index: 636

Text #1

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1595938 (Python Code)

Max Activating Token Index: 385

Text #2

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1610299 (Python Code)

Max Activating Token Index: 806

Text #3

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5145. Min Act: -0.0000

Data Index: 598891 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5227. Min Act: -0.0000

Data Index: 1626885 (Python Code)

Max Activating Token Index: 979

Text #5

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1498194 (Python Code)

Max Activating Token Index: 183

Text #6

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1445292 (Python Code)

Max Activating Token Index: 849

Text #7

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4596. Min Act: -0.0000

Data Index: 1508578 (Python Code)

Max Activating Token Index: 429

Text #8

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1482401 (Python Code)

Max Activating Token Index: 378

Text #9

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1465002 (Python Code)

Max Activating Token Index: 498

Text #10

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1589510 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.3730. Min Act: -0.0000

Data Index: 694799 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1380975 (Python Code)

Max Activating Token Index: 595

Text #13

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4129. Min Act: -0.0000

Data Index: 1465387 (Python Code)

Max Activating Token Index: 206

Text #14

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4568. Min Act: -0.0000

Data Index: 1472283 (Python Code)

Max Activating Token Index: 896

Text #15

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1553029 (Python Code)

Max Activating Token Index: 231

Text #16

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1568048 (Python Code)

Max Activating Token Index: 892

Text #17

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.3725. Min Act: -0.0000

Data Index: 587635 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.3756. Min Act: -0.0000

Data Index: 1490650 (Python Code)

Max Activating Token Index: 378

Text #19

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1006635 (C4 (Web Text))

Max Activating Token Index: 919