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

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

Neuron 2033 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.9003. Min Act: -0.0001

Data Index: 886077 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.8556. Min Act: -0.0001

Data Index: 862786 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.7222. Min Act: -0.0001

Data Index: 1258824 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.4786. Min Act: -0.0001

Data Index: 428769 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.3717. Min Act: -0.0001

Data Index: 955680 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.6746. Min Act: -0.0001

Data Index: 451211 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.5079. Min Act: -0.0001

Data Index: 1358928 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.4896. Min Act: -0.0001

Data Index: 722621 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.4638. Min Act: -0.0001

Data Index: 594614 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.4336. Min Act: -0.0001

Data Index: 266483 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.4030. Min Act: -0.0001

Data Index: 1091973 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.4126. Min Act: -0.0001

Data Index: 1174925 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.3700. Min Act: -0.0001

Data Index: 899985 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.2812. Min Act: -0.0001

Data Index: 1325733 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.2731. Min Act: -0.0001

Data Index: 828943 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.2835. Min Act: -0.0000

Data Index: 509120 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.2636. Min Act: -0.0001

Data Index: 1022285 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.2298. Min Act: -0.0001

Data Index: 1080433 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.0652. Min Act: -0.0001

Data Index: 272223 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 3.9003. Min Range: -3.9003

Max Act: 3.2246. Min Act: -0.0001

Data Index: 721563 (C4 (Web Text))

Max Activating Token Index: 754