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

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

Neuron 4854 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1565. Min Act: -0.0000

Data Index: 103330 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1359262 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1632. Min Act: -0.0000

Data Index: 1464867 (Python Code)

Max Activating Token Index: 692

Text #3

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1551. Min Act: -0.0000

Data Index: 1124693 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1596. Min Act: -0.0000

Data Index: 1003371 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1252. Min Act: -0.0000

Data Index: 5844 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1231. Min Act: -0.0000

Data Index: 670273 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1361943 (Python Code)

Max Activating Token Index: 960

Text #8

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1242864 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1212. Min Act: -0.0000

Data Index: 120206 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1232. Min Act: -0.0000

Data Index: 1122950 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1099. Min Act: -0.0000

Data Index: 730822 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1081. Min Act: -0.0000

Data Index: 646314 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1148. Min Act: -0.0000

Data Index: 649435 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1111. Min Act: -0.0000

Data Index: 927541 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1175. Min Act: -0.0000

Data Index: 818188 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1041059 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1054670 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1065. Min Act: -0.0000

Data Index: 1548264 (Python Code)

Max Activating Token Index: 786

Text #19

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1105. Min Act: -0.0000

Data Index: 1463319 (Python Code)

Max Activating Token Index: 40