Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1790 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0377. Min Range: -1.0377

Max Act: 1.0377. Min Act: -0.0002

Data Index: 320064 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9478. Min Act: -0.0002

Data Index: 314980 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 1.0377. Min Range: -1.0377

Max Act: 1.0284. Min Act: -0.0002

Data Index: 383898 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9549. Min Act: -0.0002

Data Index: 779153 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9440. Min Act: -0.0002

Data Index: 527619 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9168. Min Act: -0.0002

Data Index: 536318 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9758. Min Act: -0.0001

Data Index: 584562 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9147. Min Act: -0.0002

Data Index: 489919 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9330. Min Act: -0.0002

Data Index: 325295 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.8996. Min Act: -0.0002

Data Index: 664992 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9287. Min Act: -0.0001

Data Index: 1352633 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9505. Min Act: -0.0002

Data Index: 183788 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9352. Min Act: -0.0002

Data Index: 700402 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.9321. Min Act: -0.0002

Data Index: 1069142 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.8564. Min Act: -0.0002

Data Index: 1142161 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.8689. Min Act: -0.0002

Data Index: 1188007 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.8257. Min Act: -0.0002

Data Index: 949086 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.8161. Min Act: -0.0001

Data Index: 158356 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.8018. Min Act: -0.0001

Data Index: 589514 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 1.0377. Min Range: -1.0377

Max Act: 0.8258. Min Act: -0.0001

Data Index: 472674 (C4 (Web Text))

Max Activating Token Index: 262