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

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

Neuron 5275 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.9267. Min Act: -0.0000

Data Index: 43861 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8489. Min Act: -0.0001

Data Index: 54265 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.5327. Min Act: -0.0001

Data Index: 500706 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.3322. Min Act: -0.0001

Data Index: 25448 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.5664. Min Act: -0.0001

Data Index: 187657 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.4527. Min Act: -0.0000

Data Index: 1031021 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.4476. Min Act: -0.0000

Data Index: 774328 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.3261. Min Act: -0.0000

Data Index: 500239 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.4456. Min Act: -0.0001

Data Index: 716916 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.2232. Min Act: -0.0001

Data Index: 1290866 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.4620. Min Act: -0.0001

Data Index: 795145 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.3303. Min Act: -0.0001

Data Index: 376321 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.3290. Min Act: -0.0000

Data Index: 323484 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.4544. Min Act: -0.0000

Data Index: 1130948 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 2.9267. Min Range: -2.9267

Max Act: 1.9788. Min Act: -0.0000

Data Index: 1027951 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 2.9267. Min Range: -2.9267

Max Act: 1.9946. Min Act: -0.0001

Data Index: 747919 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.3881. Min Act: -0.0001

Data Index: 304148 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.2187. Min Act: -0.0000

Data Index: 955472 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.2880. Min Act: -0.0000

Data Index: 383595 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.0455. Min Act: -0.0000

Data Index: 732089 (C4 (Web Text))

Max Activating Token Index: 10