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

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

Neuron 1446 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.9378. Min Act: -0.0000

Data Index: 310289 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.9000. Min Act: -0.0000

Data Index: 309923 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.8384. Min Act: -0.0000

Data Index: 503245 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.7811. Min Act: -0.0000

Data Index: 1255457 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.7396. Min Act: -0.0000

Data Index: 129880 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.6007. Min Act: -0.0000

Data Index: 962579 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.7170. Min Act: -0.0000

Data Index: 287398 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.5837. Min Act: -0.0000

Data Index: 1610077 (Python Code)

Max Activating Token Index: 328

Text #8

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.6091. Min Act: -0.0000

Data Index: 573289 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.6296. Min Act: -0.0000

Data Index: 1145921 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.5072. Min Act: -0.0000

Data Index: 112186 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.5767. Min Act: -0.0000

Data Index: 1182292 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.4949. Min Act: -0.0000

Data Index: 276869 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.4851. Min Act: -0.0000

Data Index: 560190 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.4750. Min Act: -0.0000

Data Index: 1031704 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.5226. Min Act: -0.0000

Data Index: 1004962 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.5594. Min Act: -0.0000

Data Index: 603589 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.4647. Min Act: -0.0000

Data Index: 748002 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.4675. Min Act: -0.0000

Data Index: 980829 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 1.9378. Min Range: -1.9378

Max Act: 1.4532. Min Act: -0.0000

Data Index: 802087 (C4 (Web Text))

Max Activating Token Index: 717