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

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

Neuron 3944 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2157. Min Range: -5.2157

Max Act: 5.0007. Min Act: -0.0000

Data Index: 1509019 (Python Code)

Max Activating Token Index: 322

Text #1

Max Range: 5.2157. Min Range: -5.2157

Max Act: 5.2157. Min Act: -0.0000

Data Index: 1483354 (Python Code)

Max Activating Token Index: 312

Text #2

Max Range: 5.2157. Min Range: -5.2157

Max Act: 4.5733. Min Act: -0.0000

Data Index: 1570557 (Python Code)

Max Activating Token Index: 134

Text #3

Max Range: 5.2157. Min Range: -5.2157

Max Act: 4.6036. Min Act: -0.0000

Data Index: 595480 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 5.2157. Min Range: -5.2157

Max Act: 4.6100. Min Act: -0.0000

Data Index: 1435301 (Python Code)

Max Activating Token Index: 531

Text #5

Max Range: 5.2157. Min Range: -5.2157

Max Act: 4.3832. Min Act: -0.0000

Data Index: 1224608 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 5.2157. Min Range: -5.2157

Max Act: 4.1758. Min Act: -0.0000

Data Index: 1200892 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 5.2157. Min Range: -5.2157

Max Act: 4.5997. Min Act: -0.0000

Data Index: 269484 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 5.2157. Min Range: -5.2157

Max Act: 4.2258. Min Act: -0.0000

Data Index: 704292 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 5.2157. Min Range: -5.2157

Max Act: 4.0251. Min Act: -0.0000

Data Index: 1429906 (Python Code)

Max Activating Token Index: 991

Text #10

Max Range: 5.2157. Min Range: -5.2157

Max Act: 4.2155. Min Act: -0.0000

Data Index: 1531276 (Python Code)

Max Activating Token Index: 239

Text #11

Max Range: 5.2157. Min Range: -5.2157

Max Act: 3.8582. Min Act: -0.0000

Data Index: 537360 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 5.2157. Min Range: -5.2157

Max Act: 4.0156. Min Act: -0.0000

Data Index: 921357 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 5.2157. Min Range: -5.2157

Max Act: 4.1595. Min Act: -0.0000

Data Index: 244259 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 5.2157. Min Range: -5.2157

Max Act: 4.1483. Min Act: -0.0000

Data Index: 1240946 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 5.2157. Min Range: -5.2157

Max Act: 3.7479. Min Act: -0.0000

Data Index: 389390 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 5.2157. Min Range: -5.2157

Max Act: 3.8930. Min Act: -0.0000

Data Index: 1142525 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 5.2157. Min Range: -5.2157

Max Act: 3.9702. Min Act: -0.0000

Data Index: 750478 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 5.2157. Min Range: -5.2157

Max Act: 4.0785. Min Act: -0.0000

Data Index: 1282354 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 5.2157. Min Range: -5.2157

Max Act: 4.1500. Min Act: -0.0000

Data Index: 336050 (C4 (Web Text))

Max Activating Token Index: 904