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

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

Neuron 3505 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: 3.8194. Min Range: -3.8194

Max Act: 3.8194. Min Act: -0.0000

Data Index: 1439464 (Python Code)

Max Activating Token Index: 298

Text #1

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.0370. Min Act: -0.0000

Data Index: 1498421 (Python Code)

Max Activating Token Index: 308

Text #2

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.1289. Min Act: -0.0000

Data Index: 1632119 (Python Code)

Max Activating Token Index: 175

Text #3

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.2252. Min Act: -0.0000

Data Index: 1520785 (Python Code)

Max Activating Token Index: 690

Text #4

Max Range: 3.8194. Min Range: -3.8194

Max Act: 2.9160. Min Act: -0.0000

Data Index: 1422983 (Python Code)

Max Activating Token Index: 843

Text #5

Max Range: 3.8194. Min Range: -3.8194

Max Act: 2.7717. Min Act: -0.0000

Data Index: 114982 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 3.8194. Min Range: -3.8194

Max Act: 2.8782. Min Act: -0.0001

Data Index: 259263 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 3.8194. Min Range: -3.8194

Max Act: 2.6288. Min Act: -0.0000

Data Index: 1384225 (Python Code)

Max Activating Token Index: 548

Text #8

Max Range: 3.8194. Min Range: -3.8194

Max Act: 2.6276. Min Act: -0.0001

Data Index: 1140385 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 3.8194. Min Range: -3.8194

Max Act: 2.6138. Min Act: -0.0000

Data Index: 1512141 (Python Code)

Max Activating Token Index: 303

Text #10

Max Range: 3.8194. Min Range: -3.8194

Max Act: 2.6197. Min Act: -0.0001

Data Index: 295931 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 3.8194. Min Range: -3.8194

Max Act: 2.4615. Min Act: -0.0000

Data Index: 1641870 (Python Code)

Max Activating Token Index: 206

Text #12

Max Range: 3.8194. Min Range: -3.8194

Max Act: 2.9384. Min Act: -0.0000

Data Index: 1084167 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 3.8194. Min Range: -3.8194

Max Act: 2.6112. Min Act: -0.0001

Data Index: 787562 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 3.8194. Min Range: -3.8194

Max Act: 2.4337. Min Act: -0.0000

Data Index: 1390979 (Python Code)

Max Activating Token Index: 483

Text #15

Max Range: 3.8194. Min Range: -3.8194

Max Act: 2.4363. Min Act: -0.0000

Data Index: 1476140 (Python Code)

Max Activating Token Index: 34

Text #16

Max Range: 3.8194. Min Range: -3.8194

Max Act: 2.3337. Min Act: -0.0000

Data Index: 1616856 (Python Code)

Max Activating Token Index: 197

Text #17

Max Range: 3.8194. Min Range: -3.8194

Max Act: 2.4349. Min Act: -0.0000

Data Index: 644124 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 3.8194. Min Range: -3.8194

Max Act: 2.5271. Min Act: -0.0000

Data Index: 1375434 (Python Code)

Max Activating Token Index: 785

Text #19

Max Range: 3.8194. Min Range: -3.8194

Max Act: 2.3949. Min Act: -0.0000

Data Index: 514139 (C4 (Web Text))

Max Activating Token Index: 553