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

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

Neuron 3774 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1006444 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.5735. Min Act: -0.0000

Data Index: 955013 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.5856. Min Act: -0.0000

Data Index: 498207 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.5107. Min Act: -0.0000

Data Index: 1262302 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.5088. Min Act: -0.0001

Data Index: 497798 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.4715. Min Act: -0.0001

Data Index: 285 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.4780. Min Act: -0.0000

Data Index: 1268479 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.4456. Min Act: -0.0000

Data Index: 968821 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.4448. Min Act: -0.0001

Data Index: 641026 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1115466 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.4203. Min Act: -0.0000

Data Index: 1054661 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.4178. Min Act: -0.0000

Data Index: 970078 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.4304. Min Act: -0.0001

Data Index: 1200500 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.4150. Min Act: -0.0000

Data Index: 564122 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.4083. Min Act: -0.0001

Data Index: 1061157 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.3965. Min Act: -0.0000

Data Index: 356752 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.3908. Min Act: -0.0000

Data Index: 729732 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.4164. Min Act: -0.0001

Data Index: 595594 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.4026. Min Act: -0.0000

Data Index: 729368 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.5896. Min Range: -0.5896

Max Act: 0.4177. Min Act: -0.0000

Data Index: 676103 (C4 (Web Text))

Max Activating Token Index: 278