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

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

Neuron 4272 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.2062. Min Act: -0.0000

Data Index: 296307 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1623. Min Act: -0.0000

Data Index: 61226 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1519. Min Act: -0.0000

Data Index: 227820 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1018838 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1114095 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1336. Min Act: -0.0000

Data Index: 5137 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1168. Min Act: -0.0000

Data Index: 47538 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1174. Min Act: -0.0000

Data Index: 536324 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1411246 (Python Code)

Max Activating Token Index: 447

Text #9

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1230. Min Act: -0.0000

Data Index: 285911 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1181. Min Act: -0.0000

Data Index: 512224 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1037. Min Act: -0.0000

Data Index: 977436 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1195. Min Act: -0.0000

Data Index: 680054 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1184. Min Act: -0.0000

Data Index: 1300127 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1168. Min Act: -0.0000

Data Index: 960820 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1126. Min Act: -0.0000

Data Index: 355947 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1008213 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1035. Min Act: -0.0000

Data Index: 810603 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1103. Min Act: -0.0000

Data Index: 644298 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.0984. Min Act: -0.0000

Data Index: 1578028 (Python Code)

Max Activating Token Index: 960