Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2250 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.2092. Min Act: -0.0001

Data Index: 512238 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.2019. Min Act: -0.0001

Data Index: 574209 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1874. Min Act: -0.0001

Data Index: 184971 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1716. Min Act: -0.0001

Data Index: 85677 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1801. Min Act: -0.0001

Data Index: 1153323 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1641. Min Act: -0.0001

Data Index: 902751 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1594. Min Act: -0.0001

Data Index: 445967 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1471. Min Act: -0.0001

Data Index: 684630 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1628. Min Act: -0.0001

Data Index: 479351 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1615. Min Act: -0.0000

Data Index: 173286 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1671. Min Act: -0.0000

Data Index: 854160 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1601. Min Act: -0.0000

Data Index: 146181 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1563. Min Act: -0.0001

Data Index: 1066020 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1542. Min Act: -0.0000

Data Index: 297103 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1540. Min Act: -0.0000

Data Index: 1292412 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1543. Min Act: -0.0000

Data Index: 530703 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1521. Min Act: -0.0001

Data Index: 516973 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1572. Min Act: -0.0001

Data Index: 97234 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1507. Min Act: -0.0000

Data Index: 167275 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1596. Min Act: -0.0000

Data Index: 40575 (C4 (Web Text))

Max Activating Token Index: 945