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

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

Neuron 1846 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.6805. Min Act: -0.0001

Data Index: 594749 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.5678. Min Act: -0.0001

Data Index: 153998 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.4231. Min Act: -0.0001

Data Index: 259118 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.4047. Min Act: -0.0001

Data Index: 598380 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.5150. Min Act: -0.0001

Data Index: 1270542 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.3576. Min Act: -0.0001

Data Index: 630321 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.3040. Min Act: -0.0001

Data Index: 544963 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.3364. Min Act: -0.0001

Data Index: 1215769 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.3306. Min Act: -0.0001

Data Index: 1350882 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.1946. Min Act: -0.0001

Data Index: 1141684 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.1847. Min Act: -0.0001

Data Index: 526600 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.2669. Min Act: -0.0001

Data Index: 536819 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.1989. Min Act: -0.0001

Data Index: 560411 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.0421. Min Act: -0.0001

Data Index: 1066550 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.1338. Min Act: -0.0001

Data Index: 1317366 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.1588. Min Act: -0.0001

Data Index: 725650 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.2394. Min Act: -0.0001

Data Index: 791100 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.1576. Min Act: -0.0001

Data Index: 231076 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.2060. Min Act: -0.0001

Data Index: 783785 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 1.6805. Min Range: -1.6805

Max Act: 1.1843. Min Act: -0.0001

Data Index: 405610 (C4 (Web Text))

Max Activating Token Index: 863