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

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

Neuron 5495 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.7590. Min Act: -0.0000

Data Index: 1026557 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.7562. Min Act: -0.0000

Data Index: 1074057 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 2.7590. Min Range: -2.7590

Max Act: 1.8042. Min Act: -0.0000

Data Index: 978021 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 2.7590. Min Range: -2.7590

Max Act: 1.4332. Min Act: -0.0000

Data Index: 331590 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 2.7590. Min Range: -2.7590

Max Act: 1.4184. Min Act: -0.0000

Data Index: 799661 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 2.7590. Min Range: -2.7590

Max Act: 1.4240. Min Act: -0.0000

Data Index: 1125501 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 2.7590. Min Range: -2.7590

Max Act: 1.3947. Min Act: -0.0000

Data Index: 71508 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 2.7590. Min Range: -2.7590

Max Act: 1.4853. Min Act: -0.0000

Data Index: 984027 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 2.7590. Min Range: -2.7590

Max Act: 1.3818. Min Act: -0.0000

Data Index: 571946 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 2.7590. Min Range: -2.7590

Max Act: 1.4328. Min Act: -0.0000

Data Index: 817898 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 2.7590. Min Range: -2.7590

Max Act: 1.4335. Min Act: -0.0000

Data Index: 1060318 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 2.7590. Min Range: -2.7590

Max Act: 1.4131. Min Act: -0.0000

Data Index: 639112 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 2.7590. Min Range: -2.7590

Max Act: 1.1307. Min Act: -0.0000

Data Index: 550708 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 2.7590. Min Range: -2.7590

Max Act: 1.2618. Min Act: -0.0000

Data Index: 571073 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 2.7590. Min Range: -2.7590

Max Act: 1.2688. Min Act: -0.0000

Data Index: 299343 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 2.7590. Min Range: -2.7590

Max Act: 1.4144. Min Act: -0.0000

Data Index: 1076295 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 2.7590. Min Range: -2.7590

Max Act: 1.2570. Min Act: -0.0000

Data Index: 915069 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 2.7590. Min Range: -2.7590

Max Act: 1.2578. Min Act: -0.0000

Data Index: 540997 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 2.7590. Min Range: -2.7590

Max Act: 1.3161. Min Act: -0.0000

Data Index: 447737 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 2.7590. Min Range: -2.7590

Max Act: 1.1518. Min Act: -0.0000

Data Index: 1471423 (Python Code)

Max Activating Token Index: 760