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

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

Neuron 3796 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1306. Min Act: -0.0000

Data Index: 1282436 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1100. Min Act: -0.0000

Data Index: 157927 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1101. Min Act: -0.0000

Data Index: 749151 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1112. Min Act: -0.0000

Data Index: 170133 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1093. Min Act: -0.0000

Data Index: 686728 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1085. Min Act: -0.0000

Data Index: 642474 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1028. Min Act: -0.0000

Data Index: 1312669 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1062. Min Act: -0.0000

Data Index: 99613 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1287291 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1024113 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1013. Min Act: -0.0000

Data Index: 831903 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1001. Min Act: -0.0000

Data Index: 705521 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1257287 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0739. Min Act: -0.0000

Data Index: 167518 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0780. Min Act: -0.0000

Data Index: 225294 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0710. Min Act: -0.0000

Data Index: 889211 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0694. Min Act: -0.0000

Data Index: 106678 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0688. Min Act: -0.0000

Data Index: 338280 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0682. Min Act: -0.0000

Data Index: 1459438 (Python Code)

Max Activating Token Index: 716

Text #19

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0690. Min Act: -0.0000

Data Index: 710119 (C4 (Web Text))

Max Activating Token Index: 697