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

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

Neuron 691 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.6254. Min Act: -0.0001

Data Index: 595792 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.5113. Min Act: -0.0001

Data Index: 1538082 (Python Code)

Max Activating Token Index: 297

Text #2

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4670. Min Act: -0.0001

Data Index: 743815 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.5285. Min Act: -0.0001

Data Index: 1600412 (Python Code)

Max Activating Token Index: 262

Text #4

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4953. Min Act: -0.0001

Data Index: 1502860 (Python Code)

Max Activating Token Index: 985

Text #5

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4596. Min Act: -0.0001

Data Index: 1493295 (Python Code)

Max Activating Token Index: 101

Text #6

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4207. Min Act: -0.0000

Data Index: 862738 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4261. Min Act: -0.0000

Data Index: 209417 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1507782 (Python Code)

Max Activating Token Index: 63

Text #9

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4254. Min Act: -0.0001

Data Index: 1653170 (Python Code)

Max Activating Token Index: 428

Text #10

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4200. Min Act: -0.0001

Data Index: 1490965 (Python Code)

Max Activating Token Index: 171

Text #11

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4197. Min Act: -0.0001

Data Index: 1487371 (Python Code)

Max Activating Token Index: 734

Text #12

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4273. Min Act: -0.0001

Data Index: 1590703 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4244. Min Act: -0.0001

Data Index: 1457815 (Python Code)

Max Activating Token Index: 48

Text #14

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4203. Min Act: -0.0001

Data Index: 1578706 (Python Code)

Max Activating Token Index: 289

Text #15

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.3887. Min Act: -0.0000

Data Index: 484713 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.3914. Min Act: -0.0001

Data Index: 1505738 (Python Code)

Max Activating Token Index: 36

Text #17

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4053. Min Act: -0.0001

Data Index: 1472595 (Python Code)

Max Activating Token Index: 59

Text #18

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4297. Min Act: -0.0001

Data Index: 314208 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.3260. Min Act: -0.0001

Data Index: 868989 (C4 (Web Text))

Max Activating Token Index: 654