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

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

Neuron 1086 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.8071. Min Act: -0.0000

Data Index: 1443007 (Python Code)

Max Activating Token Index: 180

Text #1

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.7574. Min Act: -0.0000

Data Index: 1443782 (Python Code)

Max Activating Token Index: 416

Text #2

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.5667. Min Act: -0.0000

Data Index: 1502097 (Python Code)

Max Activating Token Index: 120

Text #3

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.4431. Min Act: -0.0000

Data Index: 1451273 (Python Code)

Max Activating Token Index: 904

Text #4

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.4466. Min Act: -0.0000

Data Index: 1393469 (Python Code)

Max Activating Token Index: 127

Text #5

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.3543. Min Act: -0.0000

Data Index: 1483196 (Python Code)

Max Activating Token Index: 735

Text #6

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.3962. Min Act: -0.0000

Data Index: 1419395 (Python Code)

Max Activating Token Index: 971

Text #7

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.4526. Min Act: -0.0000

Data Index: 1391298 (Python Code)

Max Activating Token Index: 926

Text #8

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.5066. Min Act: -0.0000

Data Index: 1565225 (Python Code)

Max Activating Token Index: 289

Text #9

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.3405. Min Act: -0.0000

Data Index: 1652554 (Python Code)

Max Activating Token Index: 281

Text #10

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.4785. Min Act: -0.0000

Data Index: 1487400 (Python Code)

Max Activating Token Index: 455

Text #11

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.4069. Min Act: -0.0000

Data Index: 1527227 (Python Code)

Max Activating Token Index: 51

Text #12

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.4376. Min Act: -0.0000

Data Index: 1565049 (Python Code)

Max Activating Token Index: 346

Text #13

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.3902. Min Act: -0.0000

Data Index: 1477044 (Python Code)

Max Activating Token Index: 497

Text #14

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.3795. Min Act: -0.0000

Data Index: 1513377 (Python Code)

Max Activating Token Index: 534

Text #15

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.4022. Min Act: -0.0000

Data Index: 1491832 (Python Code)

Max Activating Token Index: 297

Text #16

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.2703. Min Act: -0.0000

Data Index: 1619715 (Python Code)

Max Activating Token Index: 976

Text #17

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.3656. Min Act: -0.0000

Data Index: 1455823 (Python Code)

Max Activating Token Index: 255

Text #18

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.3558. Min Act: -0.0000

Data Index: 1598215 (Python Code)

Max Activating Token Index: 721

Text #19

Max Range: 1.8071. Min Range: -1.8071

Max Act: 1.3915. Min Act: -0.0000

Data Index: 1372117 (Python Code)

Max Activating Token Index: 831