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

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

Neuron 495 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.0813. Min Range: -7.0813

Max Act: 7.0813. Min Act: -0.0000

Data Index: 614823 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 7.0813. Min Range: -7.0813

Max Act: 6.6092. Min Act: -0.0000

Data Index: 393892 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 7.0813. Min Range: -7.0813

Max Act: 6.4548. Min Act: -0.0001

Data Index: 898126 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 7.0813. Min Range: -7.0813

Max Act: 6.7435. Min Act: -0.0000

Data Index: 950553 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 7.0813. Min Range: -7.0813

Max Act: 6.2765. Min Act: -0.0000

Data Index: 820394 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 7.0813. Min Range: -7.0813

Max Act: 6.5483. Min Act: -0.0001

Data Index: 1350825 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 7.0813. Min Range: -7.0813

Max Act: 6.2168. Min Act: -0.0000

Data Index: 848643 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 7.0813. Min Range: -7.0813

Max Act: 6.1497. Min Act: -0.0000

Data Index: 1347692 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 7.0813. Min Range: -7.0813

Max Act: 5.7114. Min Act: -0.0000

Data Index: 558917 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 7.0813. Min Range: -7.0813

Max Act: 5.4487. Min Act: -0.0000

Data Index: 899925 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 7.0813. Min Range: -7.0813

Max Act: 5.9189. Min Act: -0.0000

Data Index: 258776 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 7.0813. Min Range: -7.0813

Max Act: 5.7572. Min Act: -0.0000

Data Index: 1155353 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 7.0813. Min Range: -7.0813

Max Act: 5.4912. Min Act: -0.0000

Data Index: 1262705 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 7.0813. Min Range: -7.0813

Max Act: 5.4269. Min Act: -0.0000

Data Index: 321245 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 7.0813. Min Range: -7.0813

Max Act: 5.5522. Min Act: -0.0000

Data Index: 415088 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 7.0813. Min Range: -7.0813

Max Act: 5.1838. Min Act: -0.0000

Data Index: 474947 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 7.0813. Min Range: -7.0813

Max Act: 5.1805. Min Act: -0.0000

Data Index: 996410 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 7.0813. Min Range: -7.0813

Max Act: 5.4684. Min Act: -0.0000

Data Index: 229595 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 7.0813. Min Range: -7.0813

Max Act: 4.9708. Min Act: -0.0000

Data Index: 762974 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 7.0813. Min Range: -7.0813

Max Act: 4.9899. Min Act: -0.0000

Data Index: 117849 (C4 (Web Text))

Max Activating Token Index: 250