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

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

Neuron 5113 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1535519 (Python Code)

Max Activating Token Index: 734

Text #1

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5380. Min Act: -0.0000

Data Index: 669885 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5052. Min Act: -0.0000

Data Index: 1492894 (Python Code)

Max Activating Token Index: 340

Text #3

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1359271 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1082346 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5348. Min Act: -0.0000

Data Index: 235992 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4559. Min Act: -0.0000

Data Index: 879351 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5939. Min Act: -0.0000

Data Index: 1546818 (Python Code)

Max Activating Token Index: 129

Text #8

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5348. Min Act: -0.0000

Data Index: 114306 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5552. Min Act: -0.0000

Data Index: 1396054 (Python Code)

Max Activating Token Index: 453

Text #10

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1259416 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5119. Min Act: -0.0000

Data Index: 824253 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1165486 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1186969 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5702. Min Act: -0.0000

Data Index: 1579685 (Python Code)

Max Activating Token Index: 421

Text #15

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1603329 (Python Code)

Max Activating Token Index: 379

Text #16

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1438583 (Python Code)

Max Activating Token Index: 125

Text #17

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4648. Min Act: -0.0000

Data Index: 1572562 (Python Code)

Max Activating Token Index: 353

Text #18

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1445475 (Python Code)

Max Activating Token Index: 269

Text #19

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4739. Min Act: -0.0000

Data Index: 1616975 (Python Code)

Max Activating Token Index: 804