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

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

Neuron 4027 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.3406. Min Act: -0.0001

Data Index: 1335757 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2857. Min Act: -0.0001

Data Index: 210461 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2962. Min Act: -0.0001

Data Index: 801127 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2449. Min Act: -0.0001

Data Index: 278177 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2519. Min Act: -0.0001

Data Index: 609779 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2358. Min Act: -0.0001

Data Index: 903601 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2379. Min Act: -0.0001

Data Index: 236063 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2285. Min Act: -0.0001

Data Index: 855228 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2186. Min Act: -0.0001

Data Index: 336095 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2114. Min Act: -0.0001

Data Index: 662761 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2119. Min Act: -0.0001

Data Index: 554945 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2173. Min Act: -0.0001

Data Index: 755735 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2103. Min Act: -0.0001

Data Index: 1083276 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2015. Min Act: -0.0001

Data Index: 185049 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2101. Min Act: -0.0001

Data Index: 243457 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2150. Min Act: -0.0001

Data Index: 154603 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2072. Min Act: -0.0001

Data Index: 518306 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2104. Min Act: -0.0001

Data Index: 1380277 (Python Code)

Max Activating Token Index: 909

Text #18

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.1900. Min Act: -0.0001

Data Index: 1216682 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2000. Min Act: -0.0001

Data Index: 135580 (C4 (Web Text))

Max Activating Token Index: 208