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

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

Neuron 4000 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.3531. Min Act: -0.0000

Data Index: 558445 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.3092. Min Act: -0.0000

Data Index: 533506 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.2530. Min Act: -0.0000

Data Index: 962272 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.1156. Min Act: -0.0000

Data Index: 429307 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.0733. Min Act: -0.0000

Data Index: 1074686 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.1034. Min Act: -0.0000

Data Index: 303211 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.0676. Min Act: -0.0000

Data Index: 1073521 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.1074. Min Act: -0.0000

Data Index: 553583 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.1217. Min Act: -0.0000

Data Index: 1233593 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.0309. Min Act: -0.0000

Data Index: 848020 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.0303. Min Act: -0.0000

Data Index: 1265969 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.1015. Min Act: -0.0000

Data Index: 243085 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1313304 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.0496. Min Act: -0.0000

Data Index: 385457 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.0811. Min Act: -0.0000

Data Index: 1112575 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.0174. Min Act: -0.0000

Data Index: 297657 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.9865. Min Act: -0.0000

Data Index: 887235 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.9791. Min Act: -0.0000

Data Index: 975459 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.9662. Min Act: -0.0000

Data Index: 652603 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.9390. Min Act: -0.0000

Data Index: 1295470 (C4 (Web Text))

Max Activating Token Index: 407