Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 590 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5004. Min Range: -1.5004

Max Act: 1.5004. Min Act: -0.0000

Data Index: 1466742 (Python Code)

Max Activating Token Index: 803

Text #1

Max Range: 1.5004. Min Range: -1.5004

Max Act: 1.2552. Min Act: -0.0000

Data Index: 920562 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 1.5004. Min Range: -1.5004

Max Act: 1.2625. Min Act: -0.0000

Data Index: 1614535 (Python Code)

Max Activating Token Index: 293

Text #3

Max Range: 1.5004. Min Range: -1.5004

Max Act: 1.2254. Min Act: -0.0000

Data Index: 1176215 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 1.5004. Min Range: -1.5004

Max Act: 1.0697. Min Act: -0.0000

Data Index: 1575571 (Python Code)

Max Activating Token Index: 274

Text #5

Max Range: 1.5004. Min Range: -1.5004

Max Act: 1.1818. Min Act: -0.0000

Data Index: 1487077 (Python Code)

Max Activating Token Index: 242

Text #6

Max Range: 1.5004. Min Range: -1.5004

Max Act: 1.1065. Min Act: -0.0000

Data Index: 145335 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 1.5004. Min Range: -1.5004

Max Act: 1.1813. Min Act: -0.0000

Data Index: 1478032 (Python Code)

Max Activating Token Index: 307

Text #8

Max Range: 1.5004. Min Range: -1.5004

Max Act: 1.0425. Min Act: -0.0000

Data Index: 1324076 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 1.5004. Min Range: -1.5004

Max Act: 1.1018. Min Act: -0.0000

Data Index: 727895 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.9307. Min Act: -0.0000

Data Index: 796224 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 1.5004. Min Range: -1.5004

Max Act: 1.0816. Min Act: -0.0000

Data Index: 1385849 (Python Code)

Max Activating Token Index: 551

Text #12

Max Range: 1.5004. Min Range: -1.5004

Max Act: 1.0039. Min Act: -0.0000

Data Index: 313509 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.9753. Min Act: -0.0000

Data Index: 83508 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.9441. Min Act: -0.0000

Data Index: 981323 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.9901. Min Act: -0.0000

Data Index: 36358 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 1.5004. Min Range: -1.5004

Max Act: 1.0292. Min Act: -0.0000

Data Index: 956707 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.9634. Min Act: -0.0000

Data Index: 1277546 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.9388. Min Act: -0.0000

Data Index: 530251 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.9570. Min Act: -0.0000

Data Index: 318180 (C4 (Web Text))

Max Activating Token Index: 749