Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6039 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.4815. Min Act: -0.0000

Data Index: 1259038 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.3185. Min Act: -0.0000

Data Index: 369608 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.3573. Min Act: -0.0000

Data Index: 504811 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.3285. Min Act: -0.0000

Data Index: 29023 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.2210. Min Act: -0.0000

Data Index: 486475 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.1404. Min Act: -0.0000

Data Index: 899532 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.1176. Min Act: -0.0000

Data Index: 72904 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.0747. Min Act: -0.0000

Data Index: 1351083 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 1.4815. Min Range: -1.4815

Max Act: 0.9588. Min Act: -0.0000

Data Index: 927322 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 1.4815. Min Range: -1.4815

Max Act: 0.9433. Min Act: -0.0000

Data Index: 481483 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 1.4815. Min Range: -1.4815

Max Act: 0.9121. Min Act: -0.0000

Data Index: 510925 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.0039. Min Act: -0.0000

Data Index: 902004 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 1.4815. Min Range: -1.4815

Max Act: 1.0681. Min Act: -0.0000

Data Index: 174406 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 1.4815. Min Range: -1.4815

Max Act: 0.9807. Min Act: -0.0000

Data Index: 143610 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 1.4815. Min Range: -1.4815

Max Act: 0.9879. Min Act: -0.0000

Data Index: 743858 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 1.4815. Min Range: -1.4815

Max Act: 0.9753. Min Act: -0.0000

Data Index: 54808 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 1.4815. Min Range: -1.4815

Max Act: 0.9603. Min Act: -0.0000

Data Index: 239816 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 1.4815. Min Range: -1.4815

Max Act: 0.9429. Min Act: -0.0000

Data Index: 1071223 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 1.4815. Min Range: -1.4815

Max Act: 0.9399. Min Act: -0.0000

Data Index: 202825 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 1.4815. Min Range: -1.4815

Max Act: 0.9739. Min Act: -0.0000

Data Index: 666318 (C4 (Web Text))

Max Activating Token Index: 375