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

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

Neuron 4804 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0575. Min Range: -4.0575

Max Act: 4.0575. Min Act: -0.0000

Data Index: 709542 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.4532. Min Act: -0.0000

Data Index: 839415 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.4289. Min Act: -0.0000

Data Index: 564577 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.4648. Min Act: -0.0000

Data Index: 549347 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.1158. Min Act: -0.0000

Data Index: 1216068 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.3947. Min Act: -0.0000

Data Index: 610503 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 4.0575. Min Range: -4.0575

Max Act: 3.1874. Min Act: -0.0000

Data Index: 1141711 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 4.0575. Min Range: -4.0575

Max Act: 2.9811. Min Act: -0.0000

Data Index: 563565 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 4.0575. Min Range: -4.0575

Max Act: 2.8926. Min Act: -0.0000

Data Index: 420250 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 4.0575. Min Range: -4.0575

Max Act: 2.7134. Min Act: -0.0000

Data Index: 558400 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 4.0575. Min Range: -4.0575

Max Act: 2.3607. Min Act: -0.0000

Data Index: 1537818 (Python Code)

Max Activating Token Index: 480

Text #11

Max Range: 4.0575. Min Range: -4.0575

Max Act: 2.6100. Min Act: -0.0000

Data Index: 539313 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 4.0575. Min Range: -4.0575

Max Act: 2.3854. Min Act: -0.0000

Data Index: 1220491 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 4.0575. Min Range: -4.0575

Max Act: 2.2250. Min Act: -0.0000

Data Index: 138232 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 4.0575. Min Range: -4.0575

Max Act: 2.3176. Min Act: -0.0000

Data Index: 852585 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 4.0575. Min Range: -4.0575

Max Act: 2.0232. Min Act: -0.0000

Data Index: 554046 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 4.0575. Min Range: -4.0575

Max Act: 1.9150. Min Act: -0.0000

Data Index: 1419313 (Python Code)

Max Activating Token Index: 350

Text #17

Max Range: 4.0575. Min Range: -4.0575

Max Act: 1.6270. Min Act: -0.0000

Data Index: 1578324 (Python Code)

Max Activating Token Index: 670

Text #18

Max Range: 4.0575. Min Range: -4.0575

Max Act: 1.7822. Min Act: -0.0000

Data Index: 1623488 (Python Code)

Max Activating Token Index: 953

Text #19

Max Range: 4.0575. Min Range: -4.0575

Max Act: 1.6774. Min Act: -0.0000

Data Index: 1476604 (Python Code)

Max Activating Token Index: 994